NVIDIA Patches Critical RCE Flaw (CVE-2025-23316, CVSS 9.8) in Triton Inference Server

NVIDIA has released a software update addressing multiple high- and critical-severity vulnerabilities in its Triton Inference Server, a platform widely used for deploying AI models in production. The most severe issue, CVE-2025-23316 (CVSS 9.8 – Critical), resides in the Python backend of Triton, where an attacker could manipulate the model name parameter in the model control APIs to achieve remote code execution, according to NVIDIA.

The bulletin warns that a successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering. NVIDIA released patched builds: 25.08 for the main Triton Inference Server (addressing CVE-2025-23316, CVE-2025-23328, CVE-2025-23329) and 25.07 for the DALI backend (addressing CVE-2025-23268 and CVE-2025-23336).

The vulnerabilities affect all Triton Inference Server versions prior to 25.08, and NVIDIA urges customers to update immediately by installing the patched releases from the Triton Inference Server GitHub page and following the Secure Deployment Considerations Guide.