writing-skills

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional content for developers and agents on how to author and verify skills using a TDD approach. It does not perform any sensitive operations or data access.- [SAFE]: The external repository referenced in the attribution (github.com/obra/superpowers) is the source of the original skill and its presence in installation instructions is consistent with the skill's purpose.- [SAFE]: Code examples and shell commands provided (e.g., wc -w, npx skills add, and local script execution like ./render-graphs.js) are standard development tools and practices for this environment.- [SAFE]: The documentation of the ! dynamic context injection syntax is for educational purposes, explaining how to use it correctly for project-specific tooling (like git or gh commands) without introducing malicious injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:36 AM
Security Audit — agent-trust-hub — writing-skills