skills/rheinmir/setup/teach-me/Gen Agent Trust Hub

teach-me

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute code in the project environment using tools like /run, python3 -m pdb, and node --inspect. This is used to gather runtime data (state, call flows) to provide accurate explanations. The skill includes a specific rule to remove all temporary instruments (e.g., print, breakpoints) after analysis, which is a security-positive practice.
  • [PROMPT_INJECTION]: The skill ingests and executes code from the user's project, which creates a potential surface for indirect prompt injection if the project code contains malicious instructions.
  • Ingestion points: Files within the user's codebase identified for explanation.
  • Boundary markers: Not explicitly defined for the data being read.
  • Capability inventory: File system modification, shell command execution via /run, and usage of language interpreters.
  • Sanitization: None specified for the code content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:29 AM
Security Audit — agent-trust-hub — teach-me