teach
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions direct the agent to use a CLI command to open generated lesson files (HTML) for the user to review.
- [DYNAMIC_EXECUTION]: The skill generates interactive HTML lessons that incorporate reusable JavaScript-based components (simulators, widgets) from the assets directory to facilitate learning.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information and external resource data to influence the generation of teaching materials. \n
- Ingestion points: Data is read from files like MISSION.md, RESOURCES.md, learning-records/*.md, and NOTES.md within the workspace. \n
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for these data ingestion points. \n
- Capability inventory: The agent can write files (Markdown, HTML) and execute CLI commands to open files. \n
- Sanitization: The instructions do not specify validation or sanitization requirements for content extracted from external resources or user records before inclusion in lessons.
Audit Metadata