design-system
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a design system documentation and code generation workflow. Analysis of the instructions and reference materials (SYSTEM.md and DESIGN-FORMAT.md) revealed no evidence of prompt injection, data exfiltration, or malicious execution patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests repository content and user input to generate documentation and code primitives. However, this is inherent to its primary purpose and carries no elevated risk given the limited capabilities used.
- Ingestion points: Repository files (specifically DESIGN.md) and user interview responses.
- Boundary markers: None identified in the generated prose or code artifacts.
- Capability inventory: File writing (markdown documentation and CSS/React component code).
- Sanitization: No specific content sanitization or validation logic is defined beyond design-specific rules (e.g., WCAG AA contrast checks).
Audit Metadata