unity-architect

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are limited to reading specific, localized reports within a project's .unity-review/ directory and generating a text-based summary of architectural findings. It explicitly forbids re-running tools or modifying project code.
  • [SAFE]: No obfuscation, data exfiltration patterns, or suspicious command executions were detected. The skill operates within a restricted scope as a "perspective agent" in a larger review pipeline.
  • [SAFE]: The installation methods described in the README point to the author's own resources and established tools like the skills CLI from Vercel Labs, which is a trusted organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 01:15 PM
Security Audit — agent-trust-hub — unity-architect