web-design-guidelines
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill fetches and parses live guidelines from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that content directly to drive rule-checking, exposing the agent to untrusted third-party web content that could carry 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 fetches runtime instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that fetched content to extract rules and control the agent's review prompts and output format, so the remote file directly controls agent behavior and is a required dependency.
Audit Metadata