web-design-guidelines

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs the agent to fetch and use live guidelines from a public GitHub raw URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), meaning untrusted third-party content is ingested and used to drive rule application and output formatting.

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 rules and output-format instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, and that fetched content is required and directly controls the agent's prompts/output formatting during reviews.