skills/ninehills/skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFENO_CODECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown instructions and format definitions and does not include any executable scripts or binary files.
  • [COMMAND_EXECUTION]: The skill instructs the agent to open generated HTML lesson files using a CLI command (e.g., 'open') for the user's convenience.
  • [EXTERNAL_DOWNLOADS]: The skill's primary function involves researching and linking to external educational resources and communities to populate a resource list and provide citations.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes content from external websites to create lessons and reference materials.
  • Ingestion points: External URLs researched by the agent and stored in RESOURCES.md, such as blogs, forums, or primary source websites.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands in external data are provided.
  • Capability inventory: The agent can write files (HTML, Markdown) to the local directory and execute CLI commands to open those files.
  • Sanitization: No explicit sanitization or content validation steps are required by the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 06:42 AM
Security Audit — agent-trust-hub — teach