web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • External Downloads (LOW): The skill fetches content from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md to use as rules. While fetching remote instructions is a risk vector, the source is vercel-labs, which is a trusted GitHub organization.
  • Indirect Prompt Injection (LOW): The skill ingests untrusted data from both a remote URL and local user files. Evidence chain:
  • Ingestion points: SKILL.md instructions to fetch the remote command.md file.
  • Boundary markers: Absent; the skill does not explicitly define delimiters to separate guidelines from system instructions.
  • Capability inventory: The skill has file-read capabilities on the user's filesystem.
  • Sanitization: Absent; the content is applied directly as rules to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM