stitch-design-taste
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides semantic design instructions for an AI agent to generate consistent user interfaces. It enforces strict aesthetic rules (typography, color, layout) without introducing security risks.
- [NO_CODE]: There are no executable scripts, shell commands, or package dependencies included in the skill files. All instructions are natural language directives for a design-focused AI.
- [COMMAND_EXECUTION]: No shell command patterns or dynamic context injections (
!command) were detected. - [DATA_EXFILTRATION]: The skill does not access sensitive local files or perform network requests to external domains. Use of placeholders like
picsum.photosfor images is standard design practice and safe. - [PROMPT_INJECTION]: The skill includes instructions to override 'AI slop' or generic behaviors, but these are within the scope of its primary purpose (design quality) and do not attempt to bypass core safety filters or extract system prompts.
Audit Metadata