CVE-2026-53805
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedNVIDIA Spatial Intelligence Lab's (SIL) GEN3C contains an unauthenticated remote code execution vulnerability in the inference API server where the /request-inference and /seed-model endpoints deserialize raw HTTP request bodies using Python's pickle.loads() without authentication or input validation. Attackers can supply a crafted payload containing a __reduce__ gadget to the inference API port to achieve remote code execution as the inference process.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceNVIDIA GEN3C's inference API server has an unauthenticated RCE vulnerability where the /request-inference and /seed-model endpoints directly deserialize HTTP request bodies using Python's pickle.loads() function. Attackers can send crafted pickle payloads containing __reduce__ gadgets to achieve arbitrary code execution as the inference process user.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify NVIDIA GEN3C installationLocate the GEN3C inference API server installation and determine its version using package manager, Docker image tag, or software inventoryAffected if Version is within the affected release range and cannot be determined to have the vulnerability fixed
-
Verify /request-inference endpoint exposureSend a test HTTP request to the /request-inference endpoint or inspect server routing configuration to confirm the endpoint exists and is accessibleAffected if Endpoint is accessible without authentication
-
Verify /seed-model endpoint exposureSend a test HTTP request to the /seed-model endpoint or inspect server routing configuration to confirm the endpoint exists and is accessibleAffected if Endpoint is accessible without authentication
-
Inspect deserialization implementationReview the source code or decompile the inference server binary to locate the request handler functions for /request-inference and /seed-model, then check if pickle.loads() is used to deserialize request body dataAffected if Code uses pickle.loads() on raw HTTP request bodies without prior input validation or safe deserialization
If the inference API server exposes /request-inference or /seed-model endpoints without authentication and uses pickle.loads() to deserialize incoming request data, the environment is vulnerable to CVE-2026-53805.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scopedReplace pickle deserialization with safe formats (JSON/MessagePack), add authentication and input validation to the API endpoints, and network-segment the inference service to reduce exposure.
Latest GEN3C repository version containing commit db2ffe12ced12ddafcec5e0422ee46ce8520746b
- Clone or pull the GEN3C repository from https://github.com/nv-tlabs/GEN3C
- Apply the fix commit db2ffe12ced12ddafcec5e0422ee46ce8520746b (or pull latest code which should contain this fix)
- Alternatively, check for a release/tag version that includes this commit and upgrade to that version
- Rebuild and redeploy the inference API server with the patched code
- Verify that the /request-inference and /seed-model endpoints no longer use pickle.loads() with untrusted input
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation3.0 h
- Implementation12.0 h
- Testing6.0 h
- Review / QA3.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,720.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-53805 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-53805 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data