Vulnerability Monitor

The vendors, products, and vulnerabilities you care about

CVE-2025-23320

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.

Published

2025-08-06T13:15:39.633

Last Modified

2025-08-12T16:34:52.427

Status

Analyzed

Source

[email protected]

Severity

CVSSv3.1: 7.5 (HIGH)

Weaknesses

Type: Secondary
CWE-209

Affected Vendors & Products

Type	Vendor	Product	Version/Range	Vulnerable?
Application	nvidia	triton_inference_server	< 25.07	Yes
Operating System	linux	linux_kernel	-	No
Operating System	microsoft	windows	-	No

References

https://nvd.nist.gov/vuln/detail/CVE-2025-23320 US Government Resource ([email protected])
https://nvidia.custhelp.com/app/answers/detail/a_id/5687 Vendor Advisory ([email protected])
https://www.cve.org/CVERecord?id=CVE-2025-23320 Third Party Advisory ([email protected])