using-superpowers

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill primarily serves as a meta-instruction layer for managing and calling other skills across different AI agent platforms (Claude Code, Copilot CLI, Gemini CLI, Hermes, etc.).
  • [SAFE]: Instructions emphasize strict adherence to skill-loading procedures to ensure functional consistency, but they explicitly subordinate themselves to user commands, stating "User instructions always have the highest priority."
  • [SAFE]: References to platform capabilities like Bash, WebFetch, and Task are provided as documentation for tool mapping across environments and do not contain hardcoded or malicious command sequences.
  • [SAFE]: The "China-Specific Skill Routing" logic is a functional configuration for project-specific contexts (e.g., Gitee, Chinese documentation) and does not involve suspicious network or data operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 02:13 PM
Security Audit — agent-trust-hub — using-superpowers