cmd-idiot-proof-docs
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs file system write operations to update documentation. This risk is managed by a mandatory 'Approval Gate' that requires the agent to present a preview of additions, removals, and changes for manual user verification before execution.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted documentation files. Evidence: 1. Ingestion points: Documentation files intended for rewriting. 2. Boundary markers: None. 3. Capability inventory: File-write capabilities. 4. Sanitization: Manual approval gate for all edits.
- [DATA_EXFILTRATION]: No network activity, data exfiltration patterns, or attempts to access sensitive environment secrets were identified.
Audit Metadata