CVE-2025-23317: nvidia triton_inference_server Heap-based Buffer Overflow

Vulnerability summary

CVE-2025-23317 is a critical (CVSS 9.8) Heap-based Buffer Overflow vulnerability in nvidia triton_inference_server. EPSS estimates a 2.04% chance of exploitation in the next 30 days, higher than 81% of scored vulnerabilities.

Timeline

1. 06-08-2025
   PublishedVulnerability first disclosed.
2. 06-08-2025
   Last modifiedVulnerability information updated.

Description

NVIDIA Triton Inference Server contains a vulnerability in the HTTP server, where an attacker could start a reverse shell by sending a specially crafted HTTP request. A successful exploit of this vulnerability might lead to remote code execution, denial of service, data tampering, or information disclosure.

• CWE-122Heap-based Buffer OverflowA heap overflow condition is a buffer overflow, where the buffer that can be overwritten is allocated in the heap portion of memory, generally meaning that the buffer was allocated using a routine such as malloc().