superpowers-writing-plans
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes a systematic process for planning software changes, promoting best practices such as atomic tasks, unit testing (TDD), and modular design.\n- [SAFE]: No evidence of malicious behavior, data exfiltration, or prompt injection was found. The instructions are focused on documentation and organization within a development environment.\n- [SAFE]: External tool references (e.g., superpowers:subagent-driven-development) point to internal agent capabilities rather than external, untrusted sources.\n- [SAFE]: File system operations are limited to saving planning documents to a specific local directory (docs/superpowers/plans/), which is consistent with the skill's stated purpose.
Audit Metadata