copy-ai-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill references and fetches data from an external repository (github.com/VoltAgent/awesome-design-md) to determine design tokens at runtime. This ingestion of external data constitutes a vulnerability surface.
- Ingestion points: Remote DESIGN.md file located in the VoltAgent repository (https://github.com/VoltAgent/awesome-design-md/tree/main/design-md/copy-ai).
- Boundary markers: The skill does not provide delimiters or instructions to ignore potential commands embedded in the external content.
- Capability inventory: The skill is intended for UI design styling and constraint enforcement.
- Sanitization: There is no evidence of validation or sanitization for the tokens extracted from the remote source.
Audit Metadata