teach
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to open generated lesson files using a CLI command (e.g., system commands like 'open' or 'xdg-open') to facilitate user access.
- [INDIRECT_PROMPT_INJECTION]: The agent reads state and resource files from the local workspace to guide its teaching, creating a potential surface for injection if those files contain untrusted content.
- Ingestion points: The agent reads from MISSION.md, RESOURCES.md, NOTES.md, and sequential files in the ./learning-records/ directory.
- Boundary markers: There are no specific delimiters or 'ignore' instructions defined for the content processed from these workspace files.
- Capability inventory: The skill allows for writing HTML and markdown files and executing shell commands to open files.
- Sanitization: The instructions do not mandate specific sanitization or escaping of the content ingested from the workspace files.
- [DYNAMIC_EXECUTION]: The skill generates interactive HTML lessons that may include reusable scripts for quizzes, simulators, and diagram helpers, which involve the dynamic creation of executable content for the browser context.
Audit Metadata