What’s Vulnerable › Vulnerabilities

CVE-2025-23320

Description

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might lead to information disclosure.

Affected products

How to fix

Upgrade to a fixed version: NVIDIA Triton Inference Server 25.07. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2025-23320 or the next vulnerability affects your stack