teach

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from MISSION.md, RESOURCES.md, and learning records to personalize educational content, which creates a surface for indirect prompt injection. \n
  • Ingestion points: MISSION.md, RESOURCES.md, and files within the ./learning-records/ directory. \n
  • Boundary markers: None specified in the documentation format. \n
  • Capability inventory: The skill writes .html, .css, and .js files and suggests opening them via CLI tools. \n
  • Sanitization: No explicit sanitization or filtering of workspace content is mentioned. \n- [COMMAND_EXECUTION]: The instructions encourage the agent to open generated lesson files using system CLI commands to enhance the user experience. \n- [REMOTE_CODE_EXECUTION]: The skill generates interactive HTML assets, including JavaScript components like simulators and quizzes, for local lesson delivery.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:08 AM
Security Audit — agent-trust-hub — teach