CVE-2025-23316: OS Command Injection
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.
Affected Software
Event History
Frequently Asked Questions
What is the severity of CVE-2025-23316?
CVE-2025-23316 is classified as a high severity vulnerability due to its potential for remote code execution.
How do I fix CVE-2025-23316?
To fix CVE-2025-23316, upgrade to the latest version of NVIDIA Triton Inference Server that addresses this vulnerability.
What are the potential impacts of CVE-2025-23316?
Successful exploitation of CVE-2025-23316 can lead to remote code execution, potentially compromising the affected system.
Who is affected by CVE-2025-23316?
CVE-2025-23316 affects users of NVIDIA Triton Inference Server for both Windows and Linux platforms.
What components of NVIDIA Triton Inference Server are vulnerable in CVE-2025-23316?
The vulnerability in CVE-2025-23316 specifically affects the Python backend in the model control APIs.