CVE-2026-47472: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
NVIDIA TensorRT-LLM has a deserialization vulnerability in its inter-process communication layer that can be exploited by a local attacker with the same user privileges. Successful exploitation could result in code execution, information disclosure, data tampering, and denial of service. The vulnerability is identified as CWE-502 and carries a high severity rating with a CVSS score of 7.8. No patch or official remediation guidance is currently available.
AI Analysis
Technical Summary
CVE-2026-47472 is a vulnerability in NVIDIA TensorRT-LLM involving unsafe deserialization of untrusted data within its inter-process communication layer. An attacker with local access and the same user privileges could exploit this flaw to execute arbitrary code, disclose sensitive information, tamper with data, or cause denial of service. The CVSS 3.1 vector indicates low attack complexity and privileges required, no user interaction, and high impact on confidentiality, integrity, and availability. No vendor advisory or patch information is provided at this time.
Potential Impact
The vulnerability allows a local attacker with the same user privileges to potentially execute arbitrary code, access sensitive information, modify data, or disrupt service availability within the affected NVIDIA TensorRT-LLM environment. This could compromise system integrity and confidentiality, leading to significant operational impact.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for suspicious activity related to inter-process communication in TensorRT-LLM.
CVE-2026-47472: CWE-502 Deserialization of Untrusted Data in NVIDIA TensorRT-LLM
Description
NVIDIA TensorRT-LLM has a deserialization vulnerability in its inter-process communication layer that can be exploited by a local attacker with the same user privileges. Successful exploitation could result in code execution, information disclosure, data tampering, and denial of service. The vulnerability is identified as CWE-502 and carries a high severity rating with a CVSS score of 7.8. No patch or official remediation guidance is currently available.
CVSS v3.1
Score 7.8high
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-2026-47472 is a vulnerability in NVIDIA TensorRT-LLM involving unsafe deserialization of untrusted data within its inter-process communication layer. An attacker with local access and the same user privileges could exploit this flaw to execute arbitrary code, disclose sensitive information, tamper with data, or cause denial of service. The CVSS 3.1 vector indicates low attack complexity and privileges required, no user interaction, and high impact on confidentiality, integrity, and availability. No vendor advisory or patch information is provided at this time.
Potential Impact
The vulnerability allows a local attacker with the same user privileges to potentially execute arbitrary code, access sensitive information, modify data, or disrupt service availability within the affected NVIDIA TensorRT-LLM environment. This could compromise system integrity and confidentiality, leading to significant operational impact.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict local access to trusted users only and monitor for suspicious activity related to inter-process communication in TensorRT-LLM.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- nvidia
- Date Reserved
- 2026-05-19T19:55:38.727Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a569d1d68715ace43280a66
Added to database: 07/14/2026, 20:33:33 UTC
Last enriched: 07/21/2026, 22:35:51 UTC
Last updated: 08/28/2026, 22:52:11 UTC
Views: 89
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.