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.
History

Thu, 07 Aug 2025 07:30:00 +0000

Type Values Removed Values Added
First Time appeared Nvidia
Nvidia triton Inference Server
Vendors & Products Nvidia
Nvidia triton Inference Server

Wed, 06 Aug 2025 16:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}


Wed, 06 Aug 2025 13:00:00 +0000

Type Values Removed Values Added
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.
Weaknesses CWE-209
References
Metrics cvssV3_1

{'score': 7.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N'}


cve-icon MITRE

Status: PUBLISHED

Assigner: nvidia

Published: 2025-08-06T12:37:43.545Z

Updated: 2025-08-06T15:36:07.234Z

Reserved: 2025-01-14T01:06:28.099Z

Link: CVE-2025-23320

cve-icon Vulnrichment

Updated: 2025-08-06T14:37:28.533Z

cve-icon NVD

Status : Awaiting Analysis

Published: 2025-08-06T13:15:39.633

Modified: 2025-08-06T20:23:37.600

Link: CVE-2025-23320

cve-icon Redhat

No data.