taste-design

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates by ingesting user intent and project descriptions to generate a static Markdown-based design system (DESIGN.md). This process uses restricted tools (Read, Write) for the sole purpose of content generation and does not execute untrusted input.
  • [SAFE]: The instructions incorporate sophisticated grounding techniques, such as explicitly banning the fabrication of system metrics and performance data. This mitigates risks related to AI hallucinations and ensures the generated documentation remains grounded in user-provided facts.
  • [SAFE]: No obfuscation, prompt injection attempts, or unauthorized network operations were detected. All external service references (e.g., Google Stitch, picsum.photos) are to well-known and legitimate platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:42 PM