stitch-design-taste

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a stylistic framework for generating design documentation. It does not perform any sensitive file operations, network requests, or command executions. It is essentially a set of high-level prompting guidelines for UI/UX design tasks.
  • [EXTERNAL_DOWNLOADS]: The skill mentions Google Stitch (labs.google.com/stitch) and picsum.photos for placeholder images. These are well-known services used for the skill's primary purpose of design generation and do not involve suspicious remote code execution or data exfiltration.
  • [PROMPT_INJECTION]: The instructions contain strict design rules and 'anti-pattern' bans (e.g., banning specific fonts like Inter or layouts like centered heroes). These are creative constraints and stylistic preferences; they do not represent attempts to bypass AI safety filters, extract system prompts, or hijack agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 10:31 AM
Security Audit — agent-trust-hub — stitch-design-taste