superpowers
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised solely of instructional Markdown documentation and configuration metadata. It does not include any executable scripts, binaries, or automated installation hooks that could execute arbitrary code.
- [SAFE]: No prompt injection or behavior override patterns were detected. The skill specifically instructs the agent to treat local project rules and host platform safety guidelines as higher-priority authorities than the provided workflow guidance.
- [SAFE]: Command execution instructions are restricted to benign development tasks such as checking for the existence of local files and using version control (git) for code management.
- [SAFE]: No sensitive data access or network exfiltration patterns were identified. All external URLs point to the official upstream GitHub repository for the superpowers methodology.
- [SAFE]: The skill incorporates human-in-the-loop gates, requiring user approval before the agent proceeds from design to implementation phases.
Audit Metadata