cursor-principle-build-the-lever
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and configuration metadata. It contains no executable scripts, binaries, or code components.
- [NO_CODE]: No code or scripts were detected in the skill package; it functions solely as a behavioral guideline for the agent.
- [SAFE]: The instructions promote sound engineering principles like automation and verifiability. No prompt injection, data exfiltration, or obfuscation patterns were identified.
- [SAFE]: External references in
MIRROR.mdpoint to the officialcursor/pluginsGitHub repository, which is a well-known service for AI-powered development tools.
Audit Metadata