help
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides procedural logic for routing user requests to other tools. It retrieves context from local files including CONVENTIONS.md, AGENTS.md, CLAUDE.md, and wiki/business/offer.md. While it uses relative path navigation to access these files, this is used strictly for project-level configuration and documentation, not for accessing sensitive system files. The instructions also include a behavioral safety constraint ('Ask before you assert') to prevent the model from generating unsourced data or motives.
Audit Metadata