teach
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill implements a robust state-management system using local markdown and HTML files for missions, resources, and learning records.
- [COMMAND_EXECUTION]: Instructions suggest that the agent should use system CLI commands to open generated HTML lessons for the user, which is a benign functional requirement for a pedagogical tool.
- [SAFE]: The skill configuration includes a hardening measure (
disable-model-invocation: true) that restricts the agent's ability to trigger external model calls or tools autonomously. - [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or malicious persistence were identified.
Audit Metadata