skills/joker-of-gotham/chika-frontend-design-skills/vercel-web-design-guidelines/Gen Agent Trust Hub
vercel-web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, binary files, or network operations. It functions as a set of rules for the AI to follow when performing code reviews.
- [INDIRECT_PROMPT_INJECTION]: The skill processes source code (untrusted data) to identify UI violations. While this is an ingestion surface, the risk is negligible as the skill only outputs terse findings and does not execute the processed data. Standard boundary markers are implied by the instruction to 'Read actual source files'.
- [EXTERNAL_DOWNLOADS]: The skill mentions 'vercel-labs/agent-skills' as a source, which is a well-known and trusted repository. No actual downloads or remote code execution occur during the skill's operation.
Audit Metadata