local-models
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents the use of official and well-known Python packages (
routellm,gptcache) and provides shell configuration for standard local AI tooling (Ollama). All network references target legitimate services or local loopback environments. No evidence of prompt injection, data exfiltration, or persistence mechanisms was found. The instructions clearly emphasize using local models for privacy-sensitive tasks, which is a security best practice.
Audit Metadata