skills/keejkrej/matt-skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions suggest that the agent should use a CLI command to open generated lesson files (HTML) for the user. This is a standard productivity feature intended to allow the user to immediately view the content produced by the agent.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to gather information from external resources to generate its educational materials.
  • Ingestion points: External websites and articles referenced in the RESOURCES.md file and user-provided learning topics.
  • Boundary markers: There are no specific instructions or delimiters provided to separate external data from the agent's internal logic.
  • Capability inventory: The skill has the ability to write multiple file types to the local workspace and can execute shell commands to open them.
  • Sanitization: The instructions do not mention sanitizing or validating the content retrieved from external sources before it is used in lesson generation.
  • [EXTERNAL_DOWNLOADS]: The skill involves identifying and documenting external URLs (e.g., educational sites, forums) as learning resources. These are used for knowledge acquisition and community interaction and do not involve the automated execution of remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:13 PM
Security Audit — agent-trust-hub — teach