teach
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill implements a robust framework for local state management using markdown templates (MISSION.md, GLOSSARY.md, LEARNING-RECORD.md), which keeps all teaching activity confined to the designated workspace.
- [COMMAND_EXECUTION]: The skill instructs the agent to use CLI commands to open generated HTML lesson files. In the context of a local teaching assistant, this is a standard functional behavior aimed at enhancing user experience and does not represent an unauthorized execution risk.
- [SAFE]: The instructions explicitly direct the agent to rely on curated external resources rather than internal knowledge, and to cite sources, which promotes information integrity and allows the user to verify the educational content provided.
Audit Metadata