web-design-guidelines
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and use the live guidelines from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, meaning the agent will read and act on arbitrary, user-editable third‑party content (rules/output format) at runtime.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches runtime instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses the fetched content (rules and output-format instructions) to control its review prompts and behavior, creating a high-risk external dependency.
Audit Metadata