CVE-2026-24220: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
NVIDIA TensorRT-LLM contains a deserialization vulnerability in its visual gen server component. This vulnerability involves unsafe deserialization of unauthorized zeroMQ data, which could allow an attacker with high privileges to execute arbitrary code. The issue affects version 0.0 of TensorRT-LLM. The CVSS score is 6.4, indicating a medium severity level.
AI Analysis
Technical Summary
CVE-2026-24220 is a CWE-502 vulnerability in NVIDIA TensorRT-LLM's visual gen server, where unsafe deserialization of untrusted zeroMQ data can occur. An attacker with high privileges could exploit this vulnerability to execute arbitrary code on the affected system. The vulnerability affects version 0.0 of TensorRT-LLM. There is no vendor advisory or patch information available at this time, and no known exploits in the wild have been reported.
Potential Impact
Successful exploitation could lead to high impact on confidentiality, integrity, and availability due to arbitrary code execution. However, exploitation requires high privileges and no user interaction, limiting the attack vector. No known exploits have been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict access to the visual gen server component and ensure that only trusted users with appropriate privileges can interact with zeroMQ deserialization processes.
CVE-2026-24220: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
Description
NVIDIA TensorRT-LLM contains a deserialization vulnerability in its visual gen server component. This vulnerability involves unsafe deserialization of unauthorized zeroMQ data, which could allow an attacker with high privileges to execute arbitrary code. The issue affects version 0.0 of TensorRT-LLM. The CVSS score is 6.4, indicating a medium severity level.
CVSS v3.1
Score 6.4medium
Affected software
pkg:github/nvidia/TensorRT-LLMRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-24220 is a CWE-502 vulnerability in NVIDIA TensorRT-LLM's visual gen server, where unsafe deserialization of untrusted zeroMQ data can occur. An attacker with high privileges could exploit this vulnerability to execute arbitrary code on the affected system. The vulnerability affects version 0.0 of TensorRT-LLM. There is no vendor advisory or patch information available at this time, and no known exploits in the wild have been reported.
Potential Impact
Successful exploitation could lead to high impact on confidentiality, integrity, and availability due to arbitrary code execution. However, exploitation requires high privileges and no user interaction, limiting the attack vector. No known exploits have been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict access to the visual gen server component and ensure that only trusted users with appropriate privileges can interact with zeroMQ deserialization processes.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- nvidia
- Date Reserved
- 2026-01-21T19:09:35.635Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a569d1b68715ace43280977
Added to database: 07/14/2026, 20:33:31 UTC
Last enriched: 07/14/2026, 21:20:23 UTC
Last updated: 07/15/2026, 03:34:12 UTC
Views: 6
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.