web-design-guidelines
Warn
Audited by Snyk on Mar 9, 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). This skill explicitly requires fetching and parsing public guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md (see "Fetch Guidelines" / WebFetch step) and uses those fetched rules to drive how files are analyzed and reported, so untrusted third‑party content can directly influence the agent's decisions and outputs.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly WebFetches live rules at runtime from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that fetched content as the authoritative set of rules/output-format instructions, so external content directly controls the agent's prompts and is a required dependency.
Audit Metadata