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 instructs the agent to "Fetch fresh guidelines" using WebFetch from the public URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md, so it ingests untrusted third-party content that directly determines rules the agent will apply and could alter its actions.

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 control the agent's review instructions, so it is a high-risk runtime dependency.