web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from Vercel Labs' public GitHub repository at runtime.
  • Source: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md.
  • This operation targets a well-known service and a trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it retrieves external markdown files to serve as instructions for the agent.
  • Ingestion points: Content is fetched from the specified GitHub URL in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate the external instructions from the skill's logic.
  • Capability inventory: The skill requires both network access (to fetch rules) and file system read access (to audit code).
  • Sanitization: There is no evidence of sanitization or validation performed on the retrieved content before it is processed as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:56 PM
Security Audit — agent-trust-hub — web-design-guidelines