web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill fetches design guidelines and instructions from a trusted repository owned by Vercel Labs. This is a legitimate functional requirement for design auditing.
  • [PROMPT_INJECTION]: The skill architecture creates an indirect prompt injection surface by ingesting instructions from a remote source that influence the agent's behavior.
  • Ingestion points: Remote Markdown file at https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Reads local files to perform audits.
  • Sanitization: No content sanitization or validation of the remote guidelines is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 12:13 AM
Security Audit — agent-trust-hub — web-design-guidelines