TensorRT-LLM Restricted Unpickler Deserialization Exploit (Code Exec)
CVE-2026-24233 Published on July 14, 2026
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.
Vulnerability Analysis
CVE-2026-24233 can be exploited with local system access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to be very high.
Weakness Type
What is a Marshaling, Unmarshaling Vulnerability?
The application deserializes untrusted data without sufficiently verifying that the resulting data will be valid.
CVE-2026-24233 has been classified to as a Marshaling, Unmarshaling vulnerability or weakness.
Affected Versions
NVIDIA TensorRT-LLM:- Before and including v1.3.0 rc14 is affected.