vllm
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference guide for using the vLLM inference engine, containing only documentation links and operational rules.
- [SAFE]: No external dependencies, package installations, or remote code execution patterns were identified.
- [SAFE]: The skill mentions using a 'dummy key' for local server connections, which is a standard configuration for non-authenticated local inference endpoints and does not represent a credential leak.
Audit Metadata