web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository.
  • [PROMPT_INJECTION]: The skill processes instructions from a remote source, which establishes a surface for indirect prompt injection.
  • Ingestion points: Remote fetch from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md defined in SKILL.md.
  • Boundary markers: No delimiters or explicit warnings are used to differentiate remote guidelines from primary instructions.
  • Capability inventory: The agent reads specified local files and generates diagnostic output.
  • Sanitization: No validation or filtering is performed on the content retrieved from the external source.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:02 PM
Security Audit — agent-trust-hub — web-design-guidelines