rules-generator
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements robust data protection by explicitly forbidding the inclusion of secrets, API keys, or environment variables in the generated documentation.
- [SAFE]: File system interactions are limited to reading the target codebase and writing a single output file ('RULES.md'), with mandatory backup procedures to prevent data loss.
- [SAFE]: All dependencies are local to the agent environment, with no network requests, remote script downloads, or external package installations detected.
- [SAFE]: The workflow incorporates a 'verification' phase with a mandatory checklist to ensure accuracy, traceability, and adherence to safety rules before finalizing the output.
- [SAFE]: The indexing phase uses a subagent with a strictly defined read-only scope, preventing unauthorized modifications to the user's codebase during discovery.
Audit Metadata