CriticalVulnerability
CVE-2025-23317: NVIDIA Triton Inference Server HTTP server reverse shell via crafted request
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-23317
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 2.3%
Summary
NVIDIA Triton Inference Server contains a vulnerability in its HTTP server, where an attacker could start a reverse shell by sending a specially crafted HTTP request. The NVD entry states that a successful exploit might lead to remote code execution, denial of service, data tampering, or information disclosure, and it is classified as CWE-122 Heap-based Buffer Overflow.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- HighCVE-2026-65142: NVIDIA Model-Optimizer untrusted data deserializationSame vendor · NVD/CVE Database
- HighGHSA-g28h-2cmm-rj9x: langchain-nvidia-ai-endpoints has local file disclosure through VLM image inputsSame vendor · GitHub Advisory Database
- HighCVE-2026-47625: NVIDIA Triton Inference Server for Linux missing authorization flawSame vendor · NVD/CVE Database
- HighCVE-2026-16497: NVIDIA Triton Inference Server for Linux excessive iteration denial of serviceSame vendor · NVD/CVE Database
- MediumCVE-2026-47630: NVIDIA Triton Inference Server for Linux absolute path traversalSame vendor · NVD/CVE Database