Detections
Analytics
CVE-2025-23320
high
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.
References
https://www.theregister.com/2025/08/05/nvidia_triton_bug_chain/
https://www.infosecurity-magazine.com/news/vulnerabilities-nvidias-triton/
https://www.wiz.io/blog/nvidia-triton-cve-2025-23319-vuln-chain-to-ai-server
https://www.securityweek.com/nvidia-triton-vulnerabilities-pose-big-risk-to-ai-models/
https://www.darkreading.com/vulnerabilities-threats/nvidia-patches-critical-rce-vulnerability-chain
https://thehackernews.com/2025/08/nvidia-triton-bugs-let-unauthenticated.html