NVIDIA Triton Inference Server Stack Overflow Vulnerability Allowing Remote Code Execution

A stack-based buffer overflow vulnerability has been identified in NVIDIA Triton Inference Server for Windows and Linux, affecting all versions prior to 25.07. This vulnerability allows an attacker to send specially crafted HTTP requests that could lead to remote code execution, denial of service, information disclosure, or data tampering.

Impact

Exploitation of this vulnerability could result in a stack overflow, potentially allowing for remote code execution, denial of service, unauthorized information disclosure, or unauthorized data modification.

Remediation

Users are advised to update to version 25.07 or later. The latest release can be downloaded from the Triton Inference Server Releases page on GitHub.