skills/leek/agent-skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection by ingesting data from external resources to generate lesson content.\n
  • Ingestion points: External links curated in the RESOURCES.md file and user-provided learning topics.\n
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate untrusted external content from the agent's internal instructions.\n
  • Capability inventory: The skill has the capability to write persistent files to the local workspace (HTML, markdown) and is instructed to execute shell commands to open them.\n
  • Sanitization: While the skill guidelines suggest a manual policy of using 'High-trust' primary sources, there are no instructions for automated technical sanitization of the retrieved content.\n- [COMMAND_EXECUTION]: The skill instructions explicitly direct the agent to 'open the lesson file for the user by running a CLI command,' which involves the invocation of shell tools to interact with the host environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 12:06 PM
Security Audit — agent-trust-hub — teach