Executive brief
NVIDIA TensorRT-LLM, a library used to optimize the performance of large language models on Linux systems, contains a security flaw where a critical function lacks proper authentication. If exploited, an attacker could gain unauthorized control over the system, potentially leading to the theft of sensitive data or the execution of malicious code. This could compromise the integrity of AI operations and the confidentiality of the data being processed.
Technical details
A vulnerability classified as Missing Authentication for Critical Function (CWE-306) exists in NVIDIA TensorRT-LLM for Linux. The flaw allows a local attacker with high privileges to bypass authentication requirements for sensitive functions. Due to the high complexity of the attack and the requirement for elevated local permissions, the CVSS score is 6.4. Successful exploitation could enable arbitrary code execution, unauthorized data modification, and information disclosure within the affected environment. The vulnerability impacts versions up to and including v1.3.0 rc12.
Affected products
- NVIDIA TensorRT-LLM up to and including v1.3.0 rc12
Timeline
- 2026-07-14: disclosed: Initial publication of CVE-2026-24259 by NVIDIA.