1  info:
 2    name: triton-inference-server
 3    cve: CVE-2025-23336
 4    summary: NVIDIA Triton Inference Server vulnerable to denial of service via misconfigured model.
 5    details: |
 6      NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability where an attacker could cause a denial of service by loading a misconfigured model. A successful exploit of this vulnerability might lead to denial of service.
 7    cvss: CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:N/I:N/A:H
 8    severity: MEDIUM
 9    security_advise: |
10      1. Review and validate all models loaded into the Triton Inference Server to ensure they are correctly configured.
11      2. Implement input validation and error handling mechanisms to prevent misconfigured models from causing a denial of service.
12      3. Monitor server logs for unusual activity or repeated model loading failures.
13    references:
14      - https://nvd.nist.gov/vuln/detail/CVE-2025-23336
15      - https://nvidia.custhelp.com/app/answers/detail/a_id/5691
16  rule: ""