web-design-guidelines
Warn
Audited by Snyk on Feb 16, 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 instructs the agent to fetch and read live rules from the public raw GitHub URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that untrusted, user-authored content as part of its review workflow, creating a clear avenue for indirect prompt injection.
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 guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and uses that fetched content to supply the rules and output-format instructions the agent must follow, so the external file directly controls prompts/instructions.
Audit Metadata