web-design-guidelines

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires fetching and applying rules from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, so the agent reads untrusted third-party content that directly determines its checking rules and output format and could thus influence behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching runtime rules and output-format instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, which directly controls the agent's prompts/behavior and is required for the review workflow.