NVIDIA Triton Inference Server Stack Buffer Overflow Vulnerability Allowing Remote Code Execution

A stack-based buffer overflow vulnerability has been identified in NVIDIA Triton Inference Server for Windows and Linux. This vulnerability allows attackers to send specially crafted inputs that could be exploited to execute remote code, cause a denial of service, disclose sensitive information, and tamper with data. The vulnerability affects all versions prior to 25.07.

Impact

Exploitation of this vulnerability could lead to remote code execution, a denial of service, unauthorized information disclosure, and data tampering.

Remediation

Users are advised to update to version 25.07 or later. Instructions for downloading the latest version are available on the NVIDIA Triton Inference Server Releases page on GitHub.