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.md are focused on professional design logic and guidelines, lacking any patterns designed to subvert or ignore safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 10:34 AM
Security Audit — agent-trust-hub — design-system-reasoning