CVE-2025-23320

HIGH LAB

Nvidia Triton Inference Server < 25.07 - Error Information Exposure

Title source: rule

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.

Exploits (1)

github WORKING POC

by There-was-a-bird · pythonpoc

https://github.com/There-was-a-bird/triton-cve-2025-23320

View Code ZIP pw:eip

References (3)

[US Government Resource] https://nvd.nist.gov/vuln/detail/CVE-2025-23320

[Vendor Advisory] https://nvidia.custhelp.com/app/answers/detail/a_id/5687

[Third Party Advisory] https://www.cve.org/CVERecord?id=CVE-2025-23320

Scores

CVSS v3 7.5

EPSS 0.0009

EPSS Percentile 26.1%

Attack Vector NETWORK

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

Lab Environment

COMMUNITY

Community Lab

docker pull nvcr.io/nvidia/tritonserver:25.06-py3

https://github.com/There-was-a-bird/triton-cve-2025-23320

View in Library

Details

CWE

CWE-209

Status published

Products (1)

nvidia/triton_inference_server < 25.07

Published Aug 06, 2025

Tracked Since Feb 18, 2026