using-superpowers
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses emphatic, imperative language such as 'ABSOLUTELY MUST' and 'YOU DO NOT HAVE A CHOICE' to guide the agent's behavior regarding tool usage. These instructions are procedural in nature, designed to enforce a specific reasoning workflow rather than to bypass safety filters, extract system prompts, or subvert user intent. The skill explicitly clarifies that user instructions (e.g., in AGENTS.md) take the highest priority.
- [SAFE]: The skill serves as a meta-instruction set for tool management. It does not contain any executable scripts, performs no network requests (other than a reference link in the license for attribution), and does not access sensitive system files or credentials.
Audit Metadata