principle-build-the-lever
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of high-level instructions promoting software engineering best practices for AI agents. It advocates for building 'levers' (scripts, codemods, and generators) rather than performing manual edits. The document includes security-positive recommendations, such as keeping verification contracts outside the write scope of subagents to maintain integrity. No malicious code, obfuscation, or unauthorized access patterns were detected.
Audit Metadata