teach
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within a local workspace environment, managing educational content through Markdown and HTML files. No malicious behavior or data exfiltration was observed.
- [COMMAND_EXECUTION]: The instructions suggest that the agent should provide the user with a CLI command (e.g., 'open') to view generated lesson files in a browser. This is a standard, user-triggered action for local development workflows and does not execute arbitrary code automatically.
- [DATA_EXPOSURE]: The skill restricts its operations to the local directory (e.g., MISSION.md, RESOURCES.md, learning-records/). It does not access sensitive system paths, credentials, or environment variables.
- [EXTERNAL_DOWNLOADS]: The skill encourages the agent to research and link to high-quality external resources for citations. This is a routine operation for a teaching agent and does not involve downloading executable content or scripts.
Audit Metadata