CVE-2025-23320

Published: Aug 6, 2025Modified: Jun 17, 2026

7.5

Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Exploitability: 3.9 / Impact: 3.6

Source: psirt@nvidia.com (Secondary)

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 (1)

Products: Nvidia: Triton Inference Server

1 product

Triton Inference Server

Configuration A

1 vulnerable · 2 platform

Vulnerable Software	Affected Versions
Nvidia Triton Inference Server	Before 25.07

Running on/with	Platform Versions
Linux Linux Kernel	All versions
Microsoft Windows	All versions

Related CWEs

Generation of Error Message Containing Sensitive Information

The product generates an error message that includes sensitive information about its environment, users, or associated data.

References (3)

https://nvd.nist.gov/vuln/detail/CVE-2025-23320

Source: psirt@nvidia.com

US Government Resource

https://nvidia.custhelp.com/app/answers/detail/a_id/5687

Source: psirt@nvidia.com

Vendor Advisory

https://www.cve.org/CVERecord?id=CVE-2025-23320

Source: psirt@nvidia.com

Third Party Advisory

Timeline

No history available yet.