visual-design
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment to provide design audits.
- Ingestion points: Reads local project files including
tailwind.config.*,theme.ts,tokens.json, UI component files (.tsx,.jsx), and git history viagit diff --name-only HEAD~1. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded in the analyzed code.
- Capability inventory: The skill has the ability to read arbitrary project files, generate code implementations, and invoke other skills (
charting,animations,storybook). - Sanitization: There is no mention of sanitizing or filtering input data to prevent the execution of malicious instructions hidden in code comments or metadata.
Audit Metadata