Deserialization of Untrusted DataWeakness · CWE-502

CVE-2026-24233

HIGH · 8.4 CVSS v3.1 Published 2026-07-14
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
89/100
Remediation priority · High
No privileges Zero-click 5 weeks old

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 · unedited
NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization, where a local, unauthenticated attacker could cause deserialization of untrusted data. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, 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 confidence

NVIDIA TensorRT-LLM for Linux contains a deserialization vulnerability in its restricted unpickler used for model weight loading. A local, unauthenticated attacker could supply untrusted serialized data (model weights) to trigger insecure deserialization, potentially achieving code execution, privilege escalation, data tampering, or information disclosure.

MitigationEnsure only trusted and verified model weights from known-good sources are loaded; implement cryptographic validation/signing of model artifacts before deserialization; consider replacing pickle-based deserialization with safer formats.

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
High
Integrity
High
Availability
High

CVSS:3.1/AV:L/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 checks

Work through these to decide whether this CVE applies to you.

  1. Verify NVIDIA TensorRT-LLM installation
    Check if TensorRT-LLM is installed by looking for the tensorrt_llm package: `pip show tensorrt-llm` or `nvidia-smi` showing TensorRT capabilities, or check for /usr/local/tensorrt_llm directories
    Affected if TensorRT-LLM is installed and the version is within the affected range (any version using the vulnerable restricted unpickler)
  2. Identify the model weight loading mechanism
    Inspect code or configuration that loads model weights - look for usage of pickle, torch.load, or custom unpickler functions in the model loading pipeline
    Affected if The model loading code uses pickle-based deserialization (torch.load with weights_only=False, or custom unpickler) to load untrusted model weights
  3. Check for untrusted model weight sources
    Review where model weights are loaded from - check if they come from untrusted network sources, user-uploaded files, or external repositories without verification
    Affected if Model weights are loaded from untrusted sources without cryptographic validation or signature verification
  4. Examine the restricted unpickler implementation
    Locate the TensorRT-LLM unpickler code (typically in weight loading utilities) and verify if it properly restricts unsafe pickle operations
    Affected if The unpickler allows dangerous pickle operations or can be bypassed to load arbitrary pickle objects
  5. Audit model artifact handling
    Inspect configuration files and runtime logs for model loading paths, looking for lack of integrity verification (checksums, signatures) on model files
    Affected if Model weights are loaded without integrity verification mechanisms in place

A user is affected if they have NVIDIA TensorRT-LLM installed and load model weights from untrusted or unverified sources using pickle-based deserialization without cryptographic validation.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

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 data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Ensure only trusted and verified model weights from known-good sources are loaded; implement cryptographic validation/signing of model artifacts before deserialization; consider replacing pickle-based deserialization with safer formats.

Have this fixed Scoped from the published advisory
  • Consultation6.0 h
  • Implementation12.0 h
  • Testing8.0 h
  • Review / QA4.0 h
30.0 hours of engineering $5,280
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $8,448.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-24233 — 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 sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-24233 in production — separate from our analysis above.

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.

What this is

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.

What belongs here
  • 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