CVE-2026-24142: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
NVIDIA 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.
AI Analysis
Technical Summary
NVIDIA TensorRT-LLM contains a CWE-502 deserialization of untrusted data vulnerability. The unsafe deserialization of serialized handles can lead to code execution, data tampering, and information disclosure. The vulnerability requires local access with low privileges and does not require user interaction. The CVSS 3.1 base score is 6.3, reflecting medium severity with impacts on confidentiality, integrity, and availability. No patch or official remediation level has been disclosed by NVIDIA. This vulnerability affects all versions of TensorRT-LLM.
Potential Impact
Successful exploitation could allow an attacker with local low-privilege access to execute arbitrary code, modify data, or access sensitive information within the affected system. This impacts confidentiality, integrity, and availability of the system running TensorRT-LLM. There are no reports of active exploitation in the wild at this time.
Mitigation Recommendations
Patch status is not yet confirmed — check the NVIDIA vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for updates from NVIDIA. No official mitigation or temporary fix has been provided.
CVE-2026-24142: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
Description
NVIDIA 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.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
NVIDIA TensorRT-LLM contains a CWE-502 deserialization of untrusted data vulnerability. The unsafe deserialization of serialized handles can lead to code execution, data tampering, and information disclosure. The vulnerability requires local access with low privileges and does not require user interaction. The CVSS 3.1 base score is 6.3, reflecting medium severity with impacts on confidentiality, integrity, and availability. No patch or official remediation level has been disclosed by NVIDIA. This vulnerability affects all versions of TensorRT-LLM.
Potential Impact
Successful exploitation could allow an attacker with local low-privilege access to execute arbitrary code, modify data, or access sensitive information within the affected system. This impacts confidentiality, integrity, and availability of the system running TensorRT-LLM. There are no reports of active exploitation in the wild at this time.
Mitigation Recommendations
Patch status is not yet confirmed — check the NVIDIA vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for updates from NVIDIA. No official mitigation or temporary fix has been provided.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- nvidia
- Date Reserved
- 2026-01-21T19:09:27.437Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a0d2b8eba1db473622b5052
Added to database: 5/20/2026, 3:33:34 AM
Last enriched: 5/20/2026, 3:49:48 AM
Last updated: 5/21/2026, 6:16:22 AM
Views: 12
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.