teach
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions advise the agent to use CLI commands to open generated HTML lessons for the user. This is a standard workflow enhancement for viewing local documentation.
- [PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection as it reads from user-provided or previously generated files within the workspace to guide the teaching process.
- Ingestion points: The agent reads state from files including MISSION.md, RESOURCES.md, ./learning-records/.md, and ./lessons/.html.
- Boundary markers: No delimiters or 'ignore' instructions are specified to separate stored data from agent instructions.
- Capability inventory: The skill has permissions to write files to the workspace and execute shell commands to open files.
- Sanitization: There are no documented procedures for sanitizing or validating the content read from the workspace files before it is processed.
Audit Metadata