skills/utarn/engineer-skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to open generated lesson files (HTML) for the user using CLI commands. This is a convenience feature intended to improve the user experience within a development or learning environment.
  • [EXTERNAL_DOWNLOADS]: The skill encourages the agent to search for and include links to high-quality external educational resources and communities. These are documented in the RESOURCES.md file as references for the user.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads and acts upon content stored in local files such as MISSION.md and RESOURCES.md. This behavior is central to the skill's purpose as a stateful, personalized teaching assistant and does not appear to be exploitable for malicious purposes in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 08:33 AM
Security Audit — agent-trust-hub — teach