CVE-2025-23316

CRITICAL

NVIDIA Triton Inference Server < 25.08 - Remote Code Execution via Python Backend Model Name Parameter

Title source: llm
STIX 2.1

Description

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering.

References (1)

Core 1

Scores

CVSS v3 9.8
EPSS 0.0050
EPSS Percentile 66.0%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment
Exploitation none
Automatable yes
Technical Impact total

Details

CWE
CWE-78
Status published
Products (1)
nvidia/triton_inference_server < 25.08
Published Sep 17, 2025
Tracked Since Feb 18, 2026