superpowers
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a set of instructional guidelines for software development workflows. It does not contain any executable scripts, shell commands, or external dependencies.
- [SAFE]: No obfuscation, prompt injection, or unauthorized data access patterns were detected within the skill files or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided requirements to generate code and plans, which is a standard operational surface for development tools. 1. Ingestion points: User requests in the brainstorming phase (SKILL.md). 2. Boundary markers: The process uses structured output files like design.md and plan.md. 3. Capability inventory: The skill can write files and initiate subagents. 4. Sanitization: Standard validation is recommended in the bundled best practices documentation.
Audit Metadata