CVE-2025-23316 Command injection in Triton Inference Server
Attackers can achieve remote code execution, denial of service, and data tampering by manipulating model names in NVIDIA Triton Inference Server APIs.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-23316?
CVE-2025-23316 is a critical command injection vulnerability in Nvidia Triton Inference Server, published on 17 Sep 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-78
Which versions are affected by CVE-2025-23316?
It affects 1 product.
Products include Nvidia Triton Inference Server.
How do I fix CVE-2025-23316?
Apply the vendor's patch.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2025-23316 being exploited?
There is no known exploitation of CVE-2025-23316 in the wild and no public exploit code.
Other vulnerabilities in Nvidia Triton Inference Server
Sources
Also known as GHSA-j8qm-q2p6-5p6q, MINI-wfr6-66rg-64rr.