principle-encode-lessons-in-structure
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of purely instructional documentation outlining best practices for agent developers to use structural mechanisms instead of repetitive text.
- [SAFE]: No executable scripts, network requests, or sensitive data access patterns were identified in the analysis of the markdown instructions.
- [SAFE]: The configuration in
agents/openai.yamlis restrictive, explicitly disabling implicit invocation and thereby reducing the agent's attack surface.
Audit Metadata