vllm
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and examples for using the vLLM inference engine.
- [SAFE]: Authentication practices are encouraged, warning the user that endpoints are unauthenticated by default and advising the use of
--api-keyorVLLM_API_KEY. - [SAFE]: External links point to official documentation (docs.vllm.ai), official GitHub repositories (github.com/vllm-project), and the official PyPI registry.
- [SAFE]: No obfuscated code, suspicious remote execution patterns, or hardcoded sensitive credentials were detected.
Audit Metadata