teach
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the workspace, including MISSION.md, RESOURCES.md, and learning records, which could potentially contain instructions from external sources. Ingestion points: SKILL.md instructions for reading mission, resources, and learning records. Boundary markers: No specific delimiters or safety instructions provided for reading files. Capability inventory: Writing files (HTML/Markdown), executing CLI commands to open files, and network search for resources. Sanitization: No explicit validation of ingested file content described.
- [DYNAMIC_EXECUTION]: The skill generates interactive HTML files (e.g., quizzes, simulators) which involve script generation for educational tasks.
- [COMMAND_EXECUTION]: The skill instructs the agent to open generated lesson files using CLI commands for the user's convenience.
Audit Metadata