Zero-Trust Attestation
TEE
Verification
A valid hardware quote proves the TEE exists. End-to-end verification additionally proves freshness, the confidential channel, the measured workload, source provenance, and the request route where applicable.
How to read this run
Hardware verification is the first gate, not the final verdict.
71 checks validated their hardware quote and TCB policy. Only 3 also proved every applicable layer through workload identity, source provenance, and request routing. All 54 incomplete checks passed hardware and TCB verification in this run.
- 71/89 Hardware + TCB Vendor-rooted quote and configured hardware policy both passed.
- 57/88 Freshness Current evidence is bound to a verifier-owned challenge.
- 43/59 Confidential channel A TLS or application encryption key is bound to the attested environment.
- 24/89 Workload identity The measured runtime matches the expected workload configuration.
- 4/89 Source provenance The measured runtime is linked to signed source or release evidence.
- 2/88 Request route The request is cryptographically bound to the selected backend.
Each denominator includes only checks where that layer applies to the provider's claimed confidentiality model.
Verification Methodology
Tinfoil Enclaves
Fetches .well-known/tinfoil-attestation from each enclave. The response contains a gzipped, base64-encoded hardware quote. For TDX enclaves, the quote is verified through Intel DCAP Quote Verification Library (dcap-qvl) using Intel PCS collateral (override via PCCS_URL if needed). For SNP enclaves, the report is verified against AMD KDS VCEK certificates with builtin ARK/ASK roots. TLS certificate SPKI fingerprints are compared to the attested report_data.
Venice.ai / Redpill / NEAR AI (dstack)
All three providers use the same dstack attestation format. Venice returns a direct attestation; Redpill and NEAR AI return a two-layer format (gateway + model attestations). In all cases, the raw intel_quote hex is parsed as a TDX quote and verified via dcap-qvl using Intel PCS collateral (or PCCS_URL override). The quote-bound tcb_info.app_compose hash is recomputed and compared to tcb_info.compose_hash; when compose-manager actions_hash evidence is present, that is recomputed too. Provider server_verification and verified fields are completely ignored.
NVIDIA GPU Attestation
Non-empty GPU evidence payloads are submitted to NVIDIA's current NRAS endpoint, which returns a signed JWT. The JWT signature is verified against NRAS's JWKS, the issuer is pinned to nras.attestation.nvidia.com, and the eat_nonce is checked against the request nonce. Empty or malformed provider evidence and mismatched provider nonces are rejected locally before any NRAS request.
Chutes / Maple / Privatemode / Other Providers
Chutes is checked by fetching a live TEE chute's evidence endpoint, verifying the Intel TDX quote with dcap-qvl, checking that report_data binds the verifier nonce plus the ML-KEM E2E public key, and verifying NVIDIA GPU evidence when present. Chutes checks stay partial unless the workload image is digest-pinned or equivalent signed provenance is exposed. Maple Nitro checks also stay partial until expected PCR/workload provenance is configured. Privatemode is checked with a pinned Contrast CLI: the Coordinator is remotely attested, the active manifest must match the CDN manifest hash, and digest-pinned images are extracted from the verified initdata before the local proxy model path is accepted. PPQ is not counted as verified from liveness alone.