cmd-idiot-proof-docs
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses clear, task-oriented instructions for documentation formatting and does not attempt to subvert agent safety protocols or system rules.
- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files, environment variables, or perform network requests to external domains.
- [SAFE]: The skill implements a robust 'Approval Gate' that requires the agent to show a preview of additions, removals, and changes and wait for explicit user approval before modifying any files. This provides a strong manual control against unintended or malicious edits to the documentation.
Audit Metadata