CVE-2026-47473
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 where an attacker could cause a write-what-where condition. A successful exploit of this vulnerability might lead to data tampering, denial of service, and information disclosure.
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 contains a memory corruption vulnerability allowing a write-what-where condition, where an attacker can write arbitrary data to arbitrary memory locations. This type of flaw can enable remote code execution, data tampering, denial of service, and information disclosure.
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
- High
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:L/AC:H/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.
-
Verify TensorRT-LLM installationRun 'pip show tensorrt-llm' or check for tensorrt_llm Python package in site-packages, or check for TensorRT-LLM containers/imagesAffected if TensorRT-LLM is not installed on the system
-
Identify installed TensorRT-LLM versionExecute 'pip show tensorrt-llm' and note the Version field, or check 'python -c "import tensorrt; print(tensorrt.__version__)"' if availableAffected if Version cannot be determined or is lower than the fixed version listed in NVIDIA security bulletin CVE-2026-47473
-
Check for active TensorRT-LLM inference servicesLook for running processes related to TensorRT-LLM serving (e.g., Triton Inference Server with TensorRT-LLM backend, or custom inference endpoints). Use 'ps aux | grep -i tensorrt' or review container running processesAffected if TensorRT-LLM inference workload is actively running
-
Assess input exposure to TensorRT-LLMReview network configuration and access controls for any endpoints serving TensorRT-LLM inference requests. Check if the inference service accepts untrusted/network-accessible inputsAffected if TensorRT-LLM inference is network-accessible or accepts untrusted external inputs without validation or sandboxing
-
Compare against fixed versionConsult NVIDIA Security Bulletin (search for CVE-2026-47473) to obtain the fixed TensorRT-LLM version, then compare your installed version against itAffected if Installed version is lower than the fixed version specified in NVIDIA's advisory
You are affected if TensorRT-LLM is installed and running with a version lower than the fixed version specified in the NVIDIA security bulletin for CVE-2026-47473, especially if the inference workload accepts external or untrusted inputs.
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 available NVIDIA patches or upgrade to a fixed TensorRT-LLM version once released. Implement input validation and sandboxing around TensorRT-LLM inference workloads to limit attack surface.
- Consultation4.0 h
- Implementation8.0 h
- Testing12.0 h
- Review / QA6.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $8,192.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-47473 — 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-2026-47473 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