teach
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from MISSION.md, RESOURCES.md, and external web resources to generate lessons. Malicious instructions in these sources could influence the agent's behavior. (1) Ingestion points: MISSION.md, RESOURCES.md, and external URLs. (2) Boundary markers: No delimiters or ignore instructions are specified for untrusted data. (3) Capability inventory: Writing files, executing CLI commands, and generating interactive JS-based content. (4) Sanitization: No content validation or sanitization is mentioned.
- [COMMAND_EXECUTION]: The instructions direct the agent to open generated lesson files using a CLI command, which involves shell interaction with the host system.
- [DYNAMIC_EXECUTION]: The agent generates interactive HTML/JavaScript components such as quizzes and simulators for the user to run in their browser.
Audit Metadata