Route assessments

Dated explanations of what is established, what is missing, and which operator powers remain relevant. These are preliminary source/evidence reviews, not completed end-to-end devproof audits.

Assessment obligations · version 2

A route is a named client mode, recipient and model path. Plaintext inside approved attested code does not imply operator access. The question is whether an operator can obtain it or alter the computation without the client refusing.

Each cell names a concrete finding or task. “Our … missing/pending” identifies unfinished verification or evidence in this repository. It is not evidence of a provider defect. Select a cell for what was checked, what remains to prove, and a linked issue with acceptance tests.

Work in our verifier: A required check is absent or incomplete in our implementation, such as AMD report-signature verification or GPU appraisal. The linked task states what an implementation and rejection tests must establish.
Evidence we still need: A route-specific test, build reproduction or current review has not been retained. This is unfinished assessment work, not a finding that the provider lacks the protection.
Finding in the reviewed system: A dated source review or experiment identifies a specific protection boundary, such as unmeasured serving code or a substitutable reply key. Read the exact client/version and evidence scope before applying it to another deployment.
Scope of this route: A standard or retention-only path makes a different claim from client-verified confidential inference. It cannot inherit the guarantees of a separate encrypted path.
Routes differ: The provider has distinct client paths or unresolved obligations. Expand its row or follow the cell; no best-route selection or averaging is performed.

Collection is independent: “returned” includes responses an adapter rejected or could not fully check; “unavailable” means no usable response; “stale / mixed” includes samples more than 48 hours older than the snapshot. Exact observation dates and every raw check are on Measurements.

Assessments remain dated source findings as references change. Provider-wide reference differences from the retained review baseline flag re-review; they do not automatically rewrite the assessment or expand accepted policy. A changed document may be unrelated to a particular route. Follow its history and trace the dependency before assigning impact.

Promotion requires a recorded reviewer, exact client and workload versions, linked proof records and reproducible negative controls. No overall security stages are assigned. Existing internal states are retained without promotion; visible labels describe the actual work or finding. Dates refer to source review, not fresh deployment certification.

Hardware

Is platform evidence authenticated under the relevant hardware and TCB policy?

Authenticate the vendor-root chain, quote signature, TCB/debug policy and any GPU evidence required by the route. Release-signature verification alone is insufficient. Changed signatures and unacceptable TCB must reject.

Session

Are prompt recipient, reply key and freshness bound to the actual client exchange?

Bind the live channel, prompt recipient, reply key and freshness before sensitive data leaves the client. Test key replacement, replay and reply-key substitution. A receipt after disclosure is insufficient.

Code

Does measured workload identity resolve to approved, reproducible source?

Trace source, build, artifact and measurement to the approved workload, including serving code and model identity where claimed. Distinguish reproducibility from signed provenance and matching digests.

Operator access

Are operator-controlled inputs and access paths constrained by the approved computation?

Trace root/debug access, unmeasured configuration, secrets, control-plane inputs and mutable routing to actual effects on prompts and replies. A configuration finding is specific to the reviewed code and deployment.

Downstream

Are required worker hops and the requested model bound to the verified request?

Close necessary gateway-to-worker trust links and requested-model mapping. Test substituted workers, models and route fallback. A direct route can eliminate a gateway hop but still needs its model proof.

Updates

Can the client reject changes to accepted code until its approval policy authorizes them?

Identify who changes accepted values and when the client adopts them. Test an unapproved release, rollback and manifest update. Automatic adoption and independently reviewed pins imply different authority.

ACI gateway

3 paths · 3/3 returned · Reference history

4 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our boot check missing

TEE RedPill: Our boot check missing — Work in our verifier

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Phala hostname: Our boot check missing — Work in our verifier

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Ordinary RedPill: Our boot check missing — Work in our verifier

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Session · Our backend test to do

TEE RedPill: Our backend test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Phala hostname: Our backend test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Ordinary RedPill: Our backend test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Code · Our rebuild proof to do

TEE RedPill: Our rebuild proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Phala hostname: Our rebuild proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Ordinary RedPill: Our rebuild proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Operator access · Routes differ

TEE RedPill: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Phala hostname: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Ordinary RedPill: Non-TEE backend allowed — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The measured hostname policy permits a non-TEE backend; gateway attestation cannot constrain the whole plaintext computation.
Next proof / success condition: Establish and test an approved route policy that constrains every plaintext-holding backend; a gateway-only quote is insufficient.

Tracked work and acceptance tests: #30

Downstream · Routes differ

TEE RedPill: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Phala hostname: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Ordinary RedPill: Non-TEE backend allowed — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: This hostname does not enforce TEE-only serving. No request-bound backend proof closes that gap.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback. Use a route that enforces attested serving.

Tracked work and acceptance tests: #30

Updates · Approval not established

TEE RedPill: Approval not established — Several open obligations

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

Phala hostname: Approval not established — Several open obligations

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

Ordinary RedPill: Approval not established — Several open obligations

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

TEE RedPill Intel TDX

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our boot check missing Hardware

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our backend test to do Session

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our rebuild proof to do Code

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Approval not established Updates

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Phala hostname Intel TDX

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our boot check missing Hardware

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our backend test to do Session

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our rebuild proof to do Code

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Approval not established Updates

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Ordinary RedPill Intel TDX

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our boot check missing Hardware

Work in our verifier

Evidence reviewed: The adapter implements TDX quote appraisal and statement/event-log bindings. Expected MRTD and RTMR0–2 are not fully checked.
Next proof / success condition: Pin the reviewed boot profile and compare authenticated MRTD/RTMR0–2; reject a genuine quote for a different boot image.

Tracked work and acceptance tests: #27

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our backend test to do Session

Evidence we still need

Evidence reviewed: Gateway nonce and keyset bindings are implemented; no complete retained request test binds the selected backend.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Include keyset continuity and the selected backend.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Our rebuild proof to do Code

Evidence we still need

Evidence reviewed: Compose preimage and event bindings are checked by the adapter; a complete independently reproduced deployment is not retained.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Non-TEE backend allowed Operator access

Finding in the reviewed system

Evidence reviewed: The measured hostname policy permits a non-TEE backend; gateway attestation cannot constrain the whole plaintext computation.
Next proof / success condition: Establish and test an approved route policy that constrains every plaintext-holding backend; a gateway-only quote is insufficient.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Non-TEE backend allowed Downstream

Finding in the reviewed system

Evidence reviewed: This hostname does not enforce TEE-only serving. No request-bound backend proof closes that gap.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback. Use a route that enforces attested serving.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

Approval not established Updates

Several open obligations

Evidence reviewed: Compose/keyset identities are captured. The reviewed deployed profile lacks a continuity endorsement and independently established client approval.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Authenticate workload/keyset continuity.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

data/reviews/decisions/chg-b69f2fb6d3774d63dbf5612b560ea77d.json verifiers/aci.py data/routes.json

NEAR AI

3 paths · 1/2 returned · Reference history

3 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Routes differ

Gateway HTTPS: Our route proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: The gateway adapter implements selected TDX/GPU appraisal. There is no complete retained hardware-evidence chain for every recipient on this actual client path.
Next proof / success condition: Retain the authenticated CPU/GPU evidence and policy checks for the actual gateway/worker recipients; leave workload identity and session closure to their separate columns.

Tracked work and acceptance tests: #29

E2EE through gateway: Our route proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: The gateway adapter implements selected TDX/GPU appraisal. There is no complete retained hardware-evidence chain for every recipient on this actual client path.
Next proof / success condition: Retain the authenticated CPU/GPU evidence and policy checks for the actual gateway/worker recipients; leave workload identity and session closure to their separate columns.

Tracked work and acceptance tests: #29

Direct model: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #29

Session · Routes differ

Gateway HTTPS: Our request test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Some quote/key and nonce checks exist, but the actual TLS/request path and selected backend are not fully bound.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Bind the actual TLS/request path and backend.

Tracked work and acceptance tests: #29

E2EE through gateway: Reply key substitutable — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The dated route review records response-key substitution (NEAR issue 1061). Prompt-field encryption does not establish reply confidentiality; no fixed deployed exchange was verified.
Next proof / success condition: Verify a fixed, version-pinned client/protocol/deployment rejects reply-key substitution before reply disclosure; a later receipt is insufficient.

Tracked work and acceptance tests: #29

Direct model: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #29

Code · Routes differ

Gateway HTTPS: Our action check missing — Work in our verifier

Work in our verifier

Evidence reviewed: Per-model anchor and compose comparisons are implemented; compose-manager action closure is incomplete.
Next proof / success condition: Authenticate compose-manager actions through the quote/event chain and map the requested model to approved reproducible code/artifacts.

Tracked work and acceptance tests: #29

E2EE through gateway: Our action check missing — Work in our verifier

Work in our verifier

Evidence reviewed: Per-model anchor and compose comparisons are implemented; compose-manager action closure is incomplete.
Next proof / success condition: Authenticate compose-manager actions through the quote/event chain and map the requested model to approved reproducible code/artifacts.

Tracked work and acceptance tests: #29

Direct model: Our direct-path test — Evidence we still need

Evidence we still need

Evidence reviewed: The experimental direct path needs its own client, workload and accepted-policy evidence. Gateway adapter findings cannot establish this route.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #29

Operator access · Our access review to do

Gateway HTTPS: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

E2EE through gateway: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

Direct model: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

Downstream · Routes differ

Gateway HTTPS: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

E2EE through gateway: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Requested-model policy is separate from the gateway policy. The complete encrypted request, selected worker and response binding remain unverified.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

Direct model: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

Updates · Routes differ

Gateway HTTPS: Our refusal test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Repository per-model pins are distinct from on-chain provider authorization; the sending client policy was not validated end to end.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

E2EE through gateway: Our refusal test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Repository per-model pins are distinct from on-chain provider authorization; the sending client policy was not validated end to end.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

Direct model: Our direct-path test — Evidence we still need

Evidence we still need

Evidence reviewed: The experimental direct path needs its own client, workload and accepted-policy evidence. Gateway adapter findings cannot establish this route.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

Gateway HTTPS Intel TDX + GPU

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our route proof to do Hardware

Evidence we still need

Evidence reviewed: The gateway adapter implements selected TDX/GPU appraisal. There is no complete retained hardware-evidence chain for every recipient on this actual client path.
Next proof / success condition: Retain the authenticated CPU/GPU evidence and policy checks for the actual gateway/worker recipients; leave workload identity and session closure to their separate columns.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our request test to do Session

Evidence we still need

Evidence reviewed: Some quote/key and nonce checks exist, but the actual TLS/request path and selected backend are not fully bound.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Bind the actual TLS/request path and backend.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our action check missing Code

Work in our verifier

Evidence reviewed: Per-model anchor and compose comparisons are implemented; compose-manager action closure is incomplete.
Next proof / success condition: Authenticate compose-manager actions through the quote/event chain and map the requested model to approved reproducible code/artifacts.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our refusal test to do Updates

Evidence we still need

Evidence reviewed: Repository per-model pins are distinct from on-chain provider authorization; the sending client policy was not validated end to end.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

E2EE through gateway Intel TDX + GPU

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our route proof to do Hardware

Evidence we still need

Evidence reviewed: The gateway adapter implements selected TDX/GPU appraisal. There is no complete retained hardware-evidence chain for every recipient on this actual client path.
Next proof / success condition: Retain the authenticated CPU/GPU evidence and policy checks for the actual gateway/worker recipients; leave workload identity and session closure to their separate columns.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Reply key substitutable Session

Finding in the reviewed system

Evidence reviewed: The dated route review records response-key substitution (NEAR issue 1061). Prompt-field encryption does not establish reply confidentiality; no fixed deployed exchange was verified.
Next proof / success condition: Verify a fixed, version-pinned client/protocol/deployment rejects reply-key substitution before reply disclosure; a later receipt is insufficient.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our action check missing Code

Work in our verifier

Evidence reviewed: Per-model anchor and compose comparisons are implemented; compose-manager action closure is incomplete.
Next proof / success condition: Authenticate compose-manager actions through the quote/event chain and map the requested model to approved reproducible code/artifacts.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: Requested-model policy is separate from the gateway policy. The complete encrypted request, selected worker and response binding remain unverified.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our refusal test to do Updates

Evidence we still need

Evidence reviewed: Repository per-model pins are distinct from on-chain provider authorization; the sending client policy was not validated end to end.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Direct model Intel TDX + GPU

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our direct-path test Code

Evidence we still need

Evidence reviewed: The experimental direct path needs its own client, workload and accepted-policy evidence. Gateway adapter findings cannot establish this route.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Our direct-path test Updates

Evidence we still need

Evidence reviewed: The experimental direct path needs its own client, workload and accepted-policy evidence. Gateway adapter findings cannot establish this route.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #29

Evidence scope: dated repository source/review; no new live route proof is implied.

providers/near-ai.md verifiers/near_ai.py data/routes.json

Tinfoil

1 paths · 1/1 returned · Reference history

2 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our AMD check missing

Router → worker: Our AMD check missing — Work in our verifier

Work in our verifier

Evidence reviewed: Our verifier does not authenticate the AMD VCEK chain or SNP report signature. Hardware assurance is therefore unestablished here; this is a limitation of our instrument, not evidence that Tinfoil lacks hardware attestation.
Next proof / success condition: Authenticate the AMD report signature and VCEK chain against explicit roots/TCB policy, then bind the authenticated report to the measurement and session keys.

Tracked work and acceptance tests: #26

Session · Our session proof to do

Router → worker: Our session proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: Live TLS-key pin and HPKE/report-data consistency are checked, but hardware authentication, authenticated session freshness and the encrypted request remain unverified.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. First close the AMD authentication dependency.

Tracked work and acceptance tests: #26 #30

Code · Our rebuild proof to do

Router → worker: Our rebuild proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: Sigstore release provenance and measurement agreement are checked. The verifier explicitly does not independently reproduce the build.
Next proof / success condition: Independently reproduce the exact released artifact and bind it to the authenticated measured deployment.

Tracked work and acceptance tests: #30

Operator access · Our re-review to do

Router → worker: Our re-review to do — Evidence we still need

Evidence we still need

Evidence reviewed: An April 26 source audit traced two named external-config inputs to non-prompt uses for that deployment. The general schema permits unmeasured inputs; that historical result does not establish operator constraints for the currently observed reference.
Next proof / success condition: Repeat the input-to-plaintext-path analysis for the currently assessed code/configuration, retaining the exact version and relevant operator-access tests.

Tracked work and acceptance tests: #30

Downstream · Our worker test to do

Router → worker: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Our refusal test to do

Router → worker: Our refusal test to do — Evidence we still need

Evidence we still need

Evidence reviewed: The measured router configuration can pin worker repositories. Automatic release authority, client approval and a live worker request still require a scoped assessment.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Verify measured worker-repository policy on a live route.

Tracked work and acceptance tests: #30

Router → worker AMD SEV-SNP

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our AMD check missing Hardware

Work in our verifier

Evidence reviewed: Our verifier does not authenticate the AMD VCEK chain or SNP report signature. Hardware assurance is therefore unestablished here; this is a limitation of our instrument, not evidence that Tinfoil lacks hardware attestation.
Next proof / success condition: Authenticate the AMD report signature and VCEK chain against explicit roots/TCB policy, then bind the authenticated report to the measurement and session keys.

Tracked work and acceptance tests: #26

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Our session proof to do Session

Evidence we still need

Evidence reviewed: Live TLS-key pin and HPKE/report-data consistency are checked, but hardware authentication, authenticated session freshness and the encrypted request remain unverified.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. First close the AMD authentication dependency.

Tracked work and acceptance tests: #26 #30

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Our rebuild proof to do Code

Evidence we still need

Evidence reviewed: Sigstore release provenance and measurement agreement are checked. The verifier explicitly does not independently reproduce the build.
Next proof / success condition: Independently reproduce the exact released artifact and bind it to the authenticated measured deployment.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Our re-review to do Operator access

Evidence we still need

Evidence reviewed: An April 26 source audit traced two named external-config inputs to non-prompt uses for that deployment. The general schema permits unmeasured inputs; that historical result does not establish operator constraints for the currently observed reference.
Next proof / success condition: Repeat the input-to-plaintext-path analysis for the currently assessed code/configuration, retaining the exact version and relevant operator-access tests.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Our refusal test to do Updates

Evidence we still need

Evidence reviewed: The measured router configuration can pin worker repositories. Automatic release authority, client approval and a live worker request still require a scoped assessment.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Verify measured worker-repository policy on a live route.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/tinfoil.py research/review-2026-10-13/review.md data/routes.json providers/tinfoil.md

Venice

2 paths · 4/5 returned · Reference history

Hardware · Our hardware test to do

E2EE via NEAR: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

E2EE via Phala: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Session · Our session test to do

E2EE via NEAR: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

E2EE via Phala: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Code · Our code proof to do

E2EE via NEAR: Our code proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

E2EE via Phala: Our code proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Operator access · Our access review to do

E2EE via NEAR: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

E2EE via Phala: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Downstream · Our worker test to do

E2EE via NEAR: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

E2EE via Phala: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Our policy test to do

E2EE via NEAR: Our policy test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

E2EE via Phala: Our policy test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

E2EE via NEAR NEAR backend

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our code proof to do Code

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our policy test to do Updates

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

E2EE via Phala Phala backend

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our code proof to do Code

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our policy test to do Updates

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Chutes

1 paths · 5/6 returned · Reference history

1 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our GPU/RTMR checks missing

TEE models: Our GPU/RTMR checks missing — Work in our verifier

Work in our verifier

Evidence reviewed: The daily adapter implements TDX signature appraisal, nonce/key/certificate binding, debug-state and MRTD golden-set checks. It records GPU presence but does not appraise GPUs or compare the full expected boot/runtime RTMR set. The dated manual investigation performed stronger checks.
Next proof / success condition: Wire authenticated GPU appraisal and full required-register comparison into the daily adapter; reject mismatched GPU/nonce, each required register and valid-but-unpublished images. This does not establish serving-code/model identity.

Tracked work and acceptance tests: #28

Session · Our request test to do

TEE models: Our request test to do — Evidence we still need

Evidence we still need

Evidence reviewed: The daily adapter implements nonce/key checks. The retained route assessment does not contain a complete request/reply test for this client path.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Reconcile the dated manual encrypted-completion evidence with the exact client/mode.

Tracked work and acceptance tests: #30 #19

Code · Serving code unmeasured

TEE models: Serving code unmeasured — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The reviewed Chutes base-TD measurements do not commit to serve.py or model weights. Golden-set membership is not approval of the serving workload.
Next proof / success condition: Establish authenticated commitments to the actual serving code/model and test that malicious code or weight substitution is rejected before payload release.

Tracked work and acceptance tests: #31

Operator access · Code can change unmeasured

TEE models: Code can change unmeasured — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: Serving code is outside the measured registers; the base-image check cannot constrain changes to that code.
Next proof / success condition: Show the measured/approved boundary prevents operator serving-code changes that log or disclose prompts; retain a controlled rejection test.

Tracked work and acceptance tests: #31

Downstream · Model not committed

TEE models: Model not committed — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The requested model artifact and serving code are not established by the measured registers.
Next proof / success condition: Bind requested model/weights and serving code to the verified request; reject a model or artifact substitution.

Tracked work and acceptance tests: #31

Updates · Provider set only

TEE models: Provider set only — Several open obligations

Several open obligations

Evidence reviewed: The provider golden set is captured and compared; it is not an independently approved complete workload policy.
Next proof / success condition: Define independently approved complete workload expectations and test the actual client refuses unapproved code/model updates.

Tracked work and acceptance tests: #31

TEE models Intel TDX

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our GPU/RTMR checks missing Hardware

Work in our verifier

Evidence reviewed: The daily adapter implements TDX signature appraisal, nonce/key/certificate binding, debug-state and MRTD golden-set checks. It records GPU presence but does not appraise GPUs or compare the full expected boot/runtime RTMR set. The dated manual investigation performed stronger checks.
Next proof / success condition: Wire authenticated GPU appraisal and full required-register comparison into the daily adapter; reject mismatched GPU/nonce, each required register and valid-but-unpublished images. This does not establish serving-code/model identity.

Tracked work and acceptance tests: #28

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Our request test to do Session

Evidence we still need

Evidence reviewed: The daily adapter implements nonce/key checks. The retained route assessment does not contain a complete request/reply test for this client path.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released. Reconcile the dated manual encrypted-completion evidence with the exact client/mode.

Tracked work and acceptance tests: #30 #19

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Serving code unmeasured Code

Finding in the reviewed system

Evidence reviewed: The reviewed Chutes base-TD measurements do not commit to serve.py or model weights. Golden-set membership is not approval of the serving workload.
Next proof / success condition: Establish authenticated commitments to the actual serving code/model and test that malicious code or weight substitution is rejected before payload release.

Tracked work and acceptance tests: #31

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Code can change unmeasured Operator access

Finding in the reviewed system

Evidence reviewed: Serving code is outside the measured registers; the base-image check cannot constrain changes to that code.
Next proof / success condition: Show the measured/approved boundary prevents operator serving-code changes that log or disclose prompts; retain a controlled rejection test.

Tracked work and acceptance tests: #31

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Model not committed Downstream

Finding in the reviewed system

Evidence reviewed: The requested model artifact and serving code are not established by the measured registers.
Next proof / success condition: Bind requested model/weights and serving code to the verified request; reject a model or artifact substitution.

Tracked work and acceptance tests: #31

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Provider set only Updates

Several open obligations

Evidence reviewed: The provider golden set is captured and compared; it is not an independently approved complete workload policy.
Next proof / success condition: Define independently approved complete workload expectations and test the actual client refuses unapproved code/model updates.

Tracked work and acceptance tests: #31

Evidence scope: dated repository source/review; no new live route proof is implied.

verifiers/chutes.py data/audits/chutes_tee.json data/routes.json

Private Inference

3 paths · Not sampled · Reference history

3 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Routes differ

Standard: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Zero data retention: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Private beta via NEAR: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Session · Routes differ

Standard: Proxy sees prompts — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: Standard routing terminates prompt confidentiality at the provider proxy; it makes no client-to-attested-model encryption claim.
Next proof / success condition: Client-to-attested-recipient confidentiality requires a separately verified encrypted route; retention policy alone cannot establish it.

Tracked work and acceptance tests: #30

Zero data retention: Proxy sees prompts — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: Zero data retention is a retention policy, not client-to-attested-model encryption.
Next proof / success condition: Client-to-attested-recipient confidentiality requires a separately verified encrypted route; retention policy alone cannot establish it.

Tracked work and acceptance tests: #30

Private beta via NEAR: Reply key substitutable — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The inspected client leaves the reply-key header substitutable by a relay. No fixed deployment or complete session was verified.
Next proof / success condition: Verify a fixed client/protocol/deployment rejects substituted reply keys before disclosure.

Tracked work and acceptance tests: #30

Code · Routes differ

Standard: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Zero data retention: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Private beta via NEAR: No approved baseline — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The inspected browser checks quote consistency but does not compare compose/OS identity against an independently approved baseline.
Next proof / success condition: Authenticate and enforce an explicitly approved model-to-compose/OS/artifact baseline; reject a genuine quote for a different workload.

Tracked work and acceptance tests: #30

Operator access · Routes differ

Standard: Proxy sees prompts — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The documented standard route gives the proxy and selected supplier plaintext access outside a client-verified computation.
Next proof / success condition: Use a separately verified confidential route if the proxy/supplier must not read prompts; document any retained plaintext holders.

Tracked work and acceptance tests: #30

Zero data retention: Proxy sees prompts — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The documented ZDR proxy still processes plaintext outside a client-verified computation; retention enforcement was not verified.
Next proof / success condition: Use a separately verified confidential route if the proxy/supplier must not read prompts; document any retained plaintext holders.

Tracked work and acceptance tests: #30

Private beta via NEAR: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Downstream · Routes differ

Standard: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Zero data retention: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Private beta via NEAR: Our model test to do — Evidence we still need

Evidence we still need

Evidence reviewed: The browser requests a model, but rejection of a substituted attested model was not established.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Routes differ

Standard: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Zero data retention: No attested-route claim — Scope of this route

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Private beta via NEAR: No approved baseline — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The inspected client lacks an independent approved workload baseline; self-consistency does not require client approval of code changes.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Establish an authority independent of self-consistency.

Tracked work and acceptance tests: #30

Standard Provider routing

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

No attested-route claim Hardware

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Proxy sees prompts Session

Finding in the reviewed system

Evidence reviewed: Standard routing terminates prompt confidentiality at the provider proxy; it makes no client-to-attested-model encryption claim.
Next proof / success condition: Client-to-attested-recipient confidentiality requires a separately verified encrypted route; retention policy alone cannot establish it.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No attested-route claim Code

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Proxy sees prompts Operator access

Finding in the reviewed system

Evidence reviewed: The documented standard route gives the proxy and selected supplier plaintext access outside a client-verified computation.
Next proof / success condition: Use a separately verified confidential route if the proxy/supplier must not read prompts; document any retained plaintext holders.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No attested-route claim Updates

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Zero data retention Provider routing

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

No attested-route claim Hardware

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Proxy sees prompts Session

Finding in the reviewed system

Evidence reviewed: Zero data retention is a retention policy, not client-to-attested-model encryption.
Next proof / success condition: Client-to-attested-recipient confidentiality requires a separately verified encrypted route; retention policy alone cannot establish it.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No attested-route claim Code

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Proxy sees prompts Operator access

Finding in the reviewed system

Evidence reviewed: The documented ZDR proxy still processes plaintext outside a client-verified computation; retention enforcement was not verified.
Next proof / success condition: Use a separately verified confidential route if the proxy/supplier must not read prompts; document any retained plaintext holders.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No attested-route claim Updates

Scope of this route

Evidence reviewed: The documented standard/ZDR path is not a client-verified TEE route.
Next proof / success condition: Keep this path outside an attested-confidentiality claim; evaluate any future private mode as a separate client/request path.

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Private beta via NEAR Intel TDX + GPU

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Reply key substitutable Session

Finding in the reviewed system

Evidence reviewed: The inspected client leaves the reply-key header substitutable by a relay. No fixed deployment or complete session was verified.
Next proof / success condition: Verify a fixed client/protocol/deployment rejects substituted reply keys before disclosure.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No approved baseline Code

Finding in the reviewed system

Evidence reviewed: The inspected browser checks quote consistency but does not compare compose/OS identity against an independently approved baseline.
Next proof / success condition: Authenticate and enforce an explicitly approved model-to-compose/OS/artifact baseline; reject a genuine quote for a different workload.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Our model test to do Downstream

Evidence we still need

Evidence reviewed: The browser requests a model, but rejection of a substituted attested model was not established.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

No approved baseline Updates

Finding in the reviewed system

Evidence reviewed: The inspected client lacks an independent approved workload baseline; self-consistency does not require client approval of code changes.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Establish an authority independent of self-consistency.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/privateinference.md data/routes.json

Maple

2 paths · Not sampled · Reference history

16 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our hardware test to do

Via Tinfoil: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Via Privatemode: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Session · Our session test to do

Via Tinfoil: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Via Privatemode: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Code · Our EIF proof to do

Via Tinfoil: Our EIF proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: PCR0 publication and SDK policy were source-reviewed; no independent EIF rebuild or live source-to-deployment mapping was established.
Next proof / success condition: Reproduce the exact Nitro EIF on a remote builder, map all included binaries to source, and bind a live authenticated measurement to that artifact.

Tracked work and acceptance tests: #30

Via Privatemode: Our EIF proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: The Nitro source includes a Continuum sidecar; no independent EIF rebuild or deployed source-to-binary mapping was established.
Next proof / success condition: Reproduce the exact Nitro EIF on a remote builder, map all included binaries to source, and bind a live authenticated measurement to that artifact.

Tracked work and acceptance tests: #30

Operator access · Our access review to do

Via Tinfoil: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Via Privatemode: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Downstream · Our worker test to do

Via Tinfoil: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Via Privatemode: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Our policy test to do

Via Tinfoil: Our policy test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Embedded roots and signed PCR0 histories can admit old values. This is source-reviewed policy, not verified live update enforcement.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Include embedded-root and signed-history admission plus onward backend policy.

Tracked work and acceptance tests: #30

Via Privatemode: Our policy test to do — Evidence we still need

Evidence we still need

Evidence reviewed: PCR0 history and embedded policy were inspected; sidecar admission and onward update enforcement remain unverified.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Include embedded-root and signed-history admission plus onward backend policy.

Tracked work and acceptance tests: #30

Via Tinfoil Nitro → Tinfoil

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our EIF proof to do Code

Evidence we still need

Evidence reviewed: PCR0 publication and SDK policy were source-reviewed; no independent EIF rebuild or live source-to-deployment mapping was established.
Next proof / success condition: Reproduce the exact Nitro EIF on a remote builder, map all included binaries to source, and bind a live authenticated measurement to that artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our policy test to do Updates

Evidence we still need

Evidence reviewed: Embedded roots and signed PCR0 histories can admit old values. This is source-reviewed policy, not verified live update enforcement.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Include embedded-root and signed-history admission plus onward backend policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Via Privatemode Nitro → Privatemode

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our EIF proof to do Code

Evidence we still need

Evidence reviewed: The Nitro source includes a Continuum sidecar; no independent EIF rebuild or deployed source-to-binary mapping was established.
Next proof / success condition: Reproduce the exact Nitro EIF on a remote builder, map all included binaries to source, and bind a live authenticated measurement to that artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Our policy test to do Updates

Evidence we still need

Evidence reviewed: PCR0 history and embedded policy were inspected; sidecar admission and onward update enforcement remain unverified.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Include embedded-root and signed-history admission plus onward backend policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/maple.md data/routes.json

Privatemode

3 paths · Not sampled · Reference history

2 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our hardware test to do

Automatic manifest: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Pinned manifest: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Proxyless API: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Session · Routes differ

Automatic manifest: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Pinned manifest: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Proxyless API: No client attestation — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The reviewed documentation describes no client-side attestation for this path; the client does not verify the recipient through the proxy protocol.
Next proof / success condition: Establish and test client-side recipient verification for any confidential claim; provider-side checks alone are a different trust model.

Tracked work and acceptance tests: #30

Code · Our code proof to do

Automatic manifest: Our code proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Pinned manifest: Our code proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Proxyless API: Our code proof to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Operator access · Our access review to do

Automatic manifest: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Pinned manifest: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Proxyless API: Our access review to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Downstream · Our worker test to do

Automatic manifest: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Pinned manifest: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Proxyless API: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Routes differ

Automatic manifest: Provider updates auto-adopted — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: Documented default behavior may adopt the latest provider manifest after a validation failure; this does not require independent approval of the changed reference.
Next proof / success condition: Demonstrate independent approval before changed manifest admission if that guarantee is claimed; preserve the documented automatic mode as a distinct policy.

Tracked work and acceptance tests: #30

Pinned manifest: Our pin-refusal test — Evidence we still need

Evidence we still need

Evidence reviewed: A local manifest pin provides an approval boundary in the documented configuration. A mutated-reference fail-closed request test remains outstanding.
Next proof / success condition: Pin the exact client and manifest, then retain a harmless accepted request plus refusal of changed/unapproved manifest values and rollback.

Tracked work and acceptance tests: #30

Proxyless API: Our policy test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

Automatic manifest Attesting proxy

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our code proof to do Code

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Provider updates auto-adopted Updates

Finding in the reviewed system

Evidence reviewed: Documented default behavior may adopt the latest provider manifest after a validation failure; this does not require independent approval of the changed reference.
Next proof / success condition: Demonstrate independent approval before changed manifest admission if that guarantee is claimed; preserve the documented automatic mode as a distinct policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Pinned manifest Attesting proxy

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our code proof to do Code

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our pin-refusal test Updates

Evidence we still need

Evidence reviewed: A local manifest pin provides an approval boundary in the documented configuration. A mutated-reference fail-closed request test remains outstanding.
Next proof / success condition: Pin the exact client and manifest, then retain a harmless accepted request plus refusal of changed/unapproved manifest values and rollback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Proxyless API Provider-mediated

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

No client attestation Session

Finding in the reviewed system

Evidence reviewed: The reviewed documentation describes no client-side attestation for this path; the client does not verify the recipient through the proxy protocol.
Next proof / success condition: Establish and test client-side recipient verification for any confidential claim; provider-side checks alone are a different trust model.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our code proof to do Code

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace the deployed measured artifact to reviewed source/build and model identities, including mutable configuration; test an unapproved artifact.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our access review to do Operator access

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Trace operator credentials, debug access and unmeasured inputs to their effects on protected data in the exact deployed version; retain checks and counterexamples.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our policy test to do Updates

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Confidential AI

1 paths · Not sampled · Reference history

4 provider reference surfaces differ from the review baseline. Determine route relevance before relying on the dated assessment.

Hardware · Our hardware test to do

Inference API: Our hardware test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Session · Our session test to do

Inference API: Our session test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Code · Our release check to do

Inference API: Our release check to do — Work in our verifier

Work in our verifier

Evidence reviewed: Release and allowlist bytes were captured, but signatures, live measurements and source-to-artifact mapping were not verified.
Next proof / success condition: Authenticate the exact release and allowlist, link them to measured live artifacts, and preserve source/build mapping with rejection controls.

Tracked work and acceptance tests: #30

Operator access · Operator access paths

Inference API: Operator access paths — Finding in the reviewed system

Finding in the reviewed system

Evidence reviewed: The dated threat-model review identifies operator key and unencrypted control-plane access paths; public attestation alone does not close them.
Next proof / success condition: For the reviewed deployment, establish that operator-key/control-plane access cannot alter or read protected computation; retain evidence of enforcement.

Tracked work and acceptance tests: #30

Downstream · Our worker test to do

Inference API: Our worker test to do — Evidence we still need

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Updates · Our refusal test to do

Inference API: Our refusal test to do — Evidence we still need

Evidence we still need

Evidence reviewed: Published allowlists and client pins exist in the design; actual update refusal and the same-session proof were not tested.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Bind the actual same-session client pins and release policy.

Tracked work and acceptance tests: #30

Inference API TDX mesh

Reviewed 2026-10-14 by codex-source-review (not independent audit approval) · source revision ffb5b54e8cb7 · Route inventory and raw checks

Our hardware test to do Hardware

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Retain a route-scoped replay authenticating hardware signatures, TCB/debug state and required CPU/GPU evidence under the actual platform policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our session test to do Session

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Verify a harmless actual prompt/reply exchange and reject substituted recipient/reply keys, stale evidence and replay before protected data is released.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our release check to do Code

Work in our verifier

Evidence reviewed: Release and allowlist bytes were captured, but signatures, live measurements and source-to-artifact mapping were not verified.
Next proof / success condition: Authenticate the exact release and allowlist, link them to measured live artifacts, and preserve source/build mapping with rejection controls.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Operator access paths Operator access

Finding in the reviewed system

Evidence reviewed: The dated threat-model review identifies operator key and unencrypted control-plane access paths; public attestation alone does not close them.
Next proof / success condition: For the reviewed deployment, establish that operator-key/control-plane access cannot alter or read protected computation; retain evidence of enforcement.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our worker test to do Downstream

Evidence we still need

Evidence reviewed: This route has no retained proof establishing this assessment axis. A source or publication capture is insufficient.
Next proof / success condition: Bind the selected worker and requested model to the actual request; reject worker/model substitution and insecure fallback.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json

Our refusal test to do Updates

Evidence we still need

Evidence reviewed: Published allowlists and client pins exist in the design; actual update refusal and the same-session proof were not tested.
Next proof / success condition: Identify the actual client approval authority and policy revision, and test refusal of unapproved updates and rollback. Bind the actual same-session client pins and release policy.

Tracked work and acceptance tests: #30

Evidence scope: dated repository source/review; no new live route proof is implied.

research/review-2026-10-13/landscape.md data/routes.json