web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches fresh UI guidelines from Vercel Labs' official GitHub repository to perform design audits.
- [INDIRECT_PROMPT_INJECTION]: The skill relies on instructions fetched from an external URL to dictate its evaluation logic, creating a surface for indirect prompt injection.
- Ingestion points: Guidelines URL (command.md) in SKILL.md.
- Boundary markers: Absent; instructions indicate the agent should fetch and apply rules directly from the source.
- Capability inventory: The skill has permissions to read local files and perform network operations.
- Sanitization: None; the content is retrieved and processed as instructions for the agent.
Audit Metadata