chiaroscuro
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of structured markdown instructions and reference files providing detailed UI/UX design patterns, accessibility checklists, and Tailwind CSS v4 implementation standards. No executable code, remote script downloads, persistence mechanisms, or data exfiltration patterns were found. All external URLs reference well-known design resources or font foundries.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it reads project instructions, product documentation, and existing codebase content (SKILL.md, Step 1) to generate UI implementations (SKILL.md, Step 4). While no explicit boundary markers or sanitization logic are defined for this external data, the risk is mitigated by the skill's extensive internal constraints and requirement to adhere to strict design reference files. As this represents a standard functional surface for a design agent, it is considered safe.
Audit Metadata