vercel-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external configuration file for visual atmosphere and design tokens hosted on a third-party GitHub repository (VoltAgent/awesome-design-md).
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill body in
SKILL.mdspecifies that design tokens are extracted dynamically from a remoteDESIGN.mdfile at runtime. - Boundary markers: The instructions do not include any delimiters or warnings to ignore potential instructions embedded within the fetched external data.
- Capability inventory: No dangerous capabilities such as arbitrary command execution, network exfiltration, or filesystem writes were detected within the skill's own code or instructions.
- Sanitization: The skill lacks explicit validation or sanitization routines for the content retrieved from the external design repository.
Audit Metadata