web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches fresh guidelines from Vercel Labs' official GitHub repository (vercel-labs/web-interface-guidelines). This is a standard operation to ensure the agent uses the most up-to-date design standards.
  • [PROMPT_INJECTION]: The skill processes external data from a remote URL and local user files, which represents a surface for indirect prompt injection. This risk is inherent to the skill's primary purpose of auditing arbitrary code against external guidelines.
  • Ingestion points: Fetches content from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and reads local files matching user-provided patterns.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: The skill utilizes file system read access for auditing and network access to retrieve guidelines.
  • Sanitization: No specific sanitization or integrity checks are mentioned for the fetched content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:57 AM