agent-superpowers
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of Markdown methodology guides and prompt templates. No executable code, network operations, or sensitive data access patterns were detected.- [PROMPT_INJECTION]: Instructional content focuses on behavioral discipline and engineering constraints (e.g., 'Verification Iron Law', 'Anti-Over-Engineering'). These instructions aim to improve output reliability rather than bypassing safety filters or overriding system instructions.- [EXTERNAL_DOWNLOADS]: Contains references to public GitHub repositories and informational links for research purposes. These references are used for educational context and do not involve automated execution of external scripts.- [COMMAND_EXECUTION]: Provides sub-agent prompt templates that guide agents through standard development workflows using existing system tools (e.g., git, pnpm). The templates include mandatory verification gates and cross-agent reviews to validate results before reporting completion.
Audit Metadata