cmd-idiot-proof-docs
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill focuses on documentation reformatting and adheres to safety best practices by requiring user approval before editing files.
- [SAFE]: The skill enforces a mandatory human-in-the-loop approval gate. It requires the agent to display a diff of changes and obtain explicit user permission before any file modifications are executed.
- [SAFE]: Indirect prompt injection attack surface analysis:
- Ingestion points: Documentation files to be rewritten.
- Boundary markers: Not explicitly defined in the prompt instructions.
- Capability inventory: File modification (writing) via the agent's edit tools.
- Sanitization: Mitigated by the mandatory human-in-the-loop approval requirement for all changes.
Audit Metadata