web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches fresh guidelines from Vercel Labs' public GitHub repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external guideline documents and user-provided code, which could contain instructions intended to influence the agent's behavior. The external source is a recognized service. * Ingestion points: Fetches content from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and reads local UI files. * Boundary markers: None specified in the SKILL.md body. * Capability inventory: File reading and network retrieval via WebFetch. * Sanitization: Not explicitly performed on the fetched guidelines or input files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:04 PM
Security Audit — agent-trust-hub — web-design-guidelines