teach

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and act upon data from several local files, which creates a surface for indirect prompt injection if those files contain malicious instructions derived from external sources.\n
  • Ingestion points: Files including MISSION.md, RESOURCES.md, ./learning-records/.md, and ./assets/.\n
  • Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to separate data from instructions.\n
  • Capability inventory: File writing (HTML/Markdown) and CLI command execution for opening files.\n
  • Sanitization: Absent. There is no mention of escaping or validating content before processing.\n- [COMMAND_EXECUTION]: The skill instructions suggest using shell commands to interact with the host system.\n
  • Evidence: The instruction 'If possible, open the lesson file for the user by running a CLI command' in SKILL.md represents a system interaction capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 09:17 AM
Security Audit — agent-trust-hub — teach