design-system-reasoning
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: A comprehensive audit of the instructions and supporting files found no malicious patterns, sensitive data exposure, or prompt injection attempts. All identified resources serve legitimate design and development functions.
- [COMMAND_EXECUTION]: The skill ships with a PowerShell script (
scripts/scaffold-theme.ps1) used for local theme scaffolding. The script reads from local reference files and writes to user-defined paths without any external network dependency or privileged operations. - [PROMPT_INJECTION]: Instructions in
SKILL.mdare focused on professional design logic and guidelines, lacking any patterns designed to subvert or ignore safety protocols.
Audit Metadata