web-design-guidelines
Warn
Audited by Snyk on Feb 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill uses WebFetch to retrieve and parse live guidelines from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, so the agent will read and act on externally hosted, third-party content that could contain injected instructions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to fetch runtime guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and to apply the fetched rules and output-format instructions on each review, so the remote content directly controls the agent's prompts/behavior and is a required runtime dependency.
Audit Metadata