CVE-2026-47475
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 TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a reachable assertion in the sampler thread. A successful exploit of this vulnerability might lead to denial of service.
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 · moderate confidenceNVIDIA TensorRT-LLM's OpenAI-compatible inference API contains a vulnerability where an attacker can trigger a reachable assertion in the sampler thread. This assertion failure causes the sampler thread to crash, resulting in denial of service for inference requests.
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
- Local
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- None
- Integrity
- None
- Availability
- High
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:N/I:N/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 TensorRT-LLM installation and versionRun 'pip show tensorrt-llm' or check the installed package version via your package manager. If built from source, check the version tag in the repository.Affected if The installed version falls within the vulnerable range (check NVIDIA's official advisory for exact affected versions)
-
Verify OpenAI-compatible API is enabledCheck your TensorRT-LLM configuration files or startup scripts for flags like '--api' or '--openai-api' that enable the OpenAI-compatible endpoint. Also check if the server is running with endpoints like /v1/chat/completions or /v1/completions.Affected if The OpenAI-compatible API endpoints are explicitly enabled and exposed
-
Determine API network exposureReview server/network configuration to identify if the inference API is bound to a public or untrusted network interface. Check for listening addresses (0.0.0.0 vs 127.0.0.1) and any firewall or proxy rules.Affected if The API is accessible from untrusted network segments or the public internet
-
Check for existing sampler thread crash logsExamine TensorRT-LLM server logs for assertion failures, sampler thread crashes, or 'abort' signals in the timeframe of suspicious requests.Affected if Recent logs show sampler thread crashes or assertion failures without known benign causes
You are affected if TensorRT-LLM with an enabled OpenAI-compatible API is running and your version is within the vulnerable range, especially if the API is exposed to untrusted clients.
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.
From vendor dataApply NVIDIA's TensorRT-LLM security patch when available. As an interim measure, restrict or monitor API access to untrusted clients to prevent malicious input sequences from reaching the sampler.
- Consultation4.0 h
- Implementation8.0 h
- Testing6.0 h
- Review / QA4.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-47475 — 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-2026-47475 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