web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from a public repository belonging to a well-known organization (Vercel Labs).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes instructions fetched from an external URL to perform its audit.
  • Ingestion points: Fetches command.md from GitHub in SKILL.md.
  • Boundary markers: None; the agent is instructed to follow the rules found in the fetched content.
  • Capability inventory: Reading local files and fetching remote content.
  • Sanitization: No specific sanitization or filtering is applied to the fetched instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 01:07 PM