CVE-2026-24233

Published Jul 14, 2026 CVSS 3.1 · 8.4 High EPSS < 1% KEV · Not listed
Description
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.

Analysis

AI-generated

Technical impact

The vulnerability stems from an insecure unpickling routine used during model weight deserialization in NVIDIA TensorRT‑LLM for Linux. The routine accepts untrusted data, allowing a local, unauthenticated attacker to cause arbitrary code execution. Successful exploitation could result in privilege escalation, data tampering, and information disclosure, compromising the confidentiality of the host system.

Affected Systems

NVIDIA TensorRT‑LLM for Linux is affected. All installations of this product are potentially vulnerable until a patch is applied or mitigations are in place.

Risk and Exploitability

The CVSS score of 8.4 marks this flaw as high severity, but the EPSS score of less than 1% indicates a very low probability of exploitation. The vulnerability is not listed in the CISA KEV catalog. Attack attempts would require local, unauthenticated access, suggesting that any user or process that can load user‑supplied model weights is a potential vector for exploitation.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Check NVIDIA for any available patch or update that addresses the restricted unpickler bug.
  • Validate model weight files before deserialization, ensuring that only trusted, signed files are used.
  • Restrict file system permissions so that only authorized processes can load or modify model weight files, limiting the scope of any deserialization attack.

Generated by OpenCVE AI on August 1, 2026 at 09:18 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Title Insecure Unpickler in NVIDIA TensorRT‑LLM Enables Local Code Execution
Type Values Removed Values Added
Title Insecure Unpickler in NVIDIA TensorRT‑LLM Enables Local Code Execution
Type Values Removed Values Added
Title Untrusted Deserialization in NVIDIA TensorRT‑LLM Leading to Local Code Execution
Type Values Removed Values Added
Title Untrusted Deserialization in NVIDIA TensorRT‑LLM Leading to Local Code Execution
Type Values Removed Values Added
Title Deserialization Vulnerability in NVIDIA TensorRT‑LLM Enabling Local Code Execution
Type Values Removed Values Added
Title Deserialization Vulnerability in NVIDIA TensorRT‑LLM Enabling Local Code Execution
Type Values Removed Values Added
First Time appeared Nvidia
Nvidia tensorrt-llm
Vendors & Products Nvidia
Nvidia tensorrt-llm
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
Description 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.
Weaknesses CWE-502
References
Metrics cvssV3_1

{'score': 8.4, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}

Weaknesses
  • CWE-502

    Deserialization of Untrusted Data

Sources

Status
PUBLISHED
Assigner
nvidia
Published
Updated
Jul 15, 2026, 2:15 PM
Reserved
Jan 21, 2026, 7:09 PM
Status
Deferred
Published
Jul 14, 2026, 9:16 PM
Modified
Oct 24, 2026, 9:10 PM