CVE-2026-24142
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 TRT-LLM for any platform contains a deserialization vulnerability and unsafe serialized handle. A successful exploit of this vulnerability might lead to code execution, data tampering, 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 TRT-LLM contains a deserialization vulnerability where unsafe handling of serialized data/handles allows attackers to potentially execute arbitrary code, tamper with data, or disclose sensitive information. The vulnerability stems from improper validation during deserialization of untrusted input.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 1.2CVSS 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 TensorRT LLM installationRun 'pip list | grep tensorrt' or check for the tensorrt_llm package in your Python environmentAffected if tensorrt_llm is installed with version less than 1.2.0
-
Determine installed TensorRT LLM versionRun 'pip show tensorrt-llm' or 'python -c "import tensorrt_llm; print(tensorrt_llm.__version__)"' to get the exact version numberAffected if The version reported is lower than 1.2.0 or the version cannot be determined (indicating an old release)
-
Locate serialized model or engine filesSearch for .engine, .safetensors, or other serialized model files in your model directories - check paths like /models, ~/tensorrt_models, or custom model paths used in your inference pipelinesAffected if Serialized model files exist and are loaded by the TensorRT LLM runtime
-
Inspect deserialization code pathsReview application code that loads TensorRT LLM models - look for functions like 'load_engine', 'from_serialized', 'deserialize', or model loading pipelines that accept file paths or serialized buffersAffected if Code loads serialized content from files, network sources, or user-controlled paths without validation
You are affected if TensorRT LLM version is below 1.2.0 AND your system loads or processes serialized model data, checkpoints, or engine files.
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 · scoped1.2
Apply vendor-provided patches when available; avoid deserializing data from untrusted sources and implement strict input validation on serialized handles. Consider migrating to safer serialization formats if possible.
TensorRT LLM version 1.2 or later
- 1. Identify the current installed version of TensorRT LLM by running `pip show tensorrt_llm` or checking your container image tag
- 2. If running TensorRT LLM version < 1.2, plan for upgrade to version 1.2 or later
- 3. Back up any serialized models, configurations, or custom plugins that may have been created with the vulnerable version
- 4. Upgrade TensorRT LLM by running `pip install --upgrade tensorrt_llm` or pulling the version 1.2+ container image
- 5. After upgrade, re-validate any serialized model files or handles before use to ensure compatibility with the patched version
- 6. Verify the upgrade was successful by confirming the installed version is >= 1.2
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation4.0 h
- Implementation16.0 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 $10,496.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-24142 — 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-2026-24142 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