design

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured workflows for visual design tasks, including art creation, branding, and theme generation. The instructions are focused on aesthetic quality and design philosophy.
  • [DATA_EXFILTRATION]: The skill references a local directory ./canvas-fonts to select typography. This is a standard functional requirement for a design-focused skill and does not involve sensitive file access, network operations, or data exfiltration.
  • [PROMPT_INJECTION]: The skill includes a 'Refine' step that simulates user feedback to encourage higher quality output. This is a steering technique for output improvement and does not attempt to bypass safety guidelines or override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:19 PM