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 explicitly instructs the agent to "Fetch the latest guidelines" from a public raw GitHub URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) and to "Use WebFetch to retrieve the latest rules" so the agent will ingest and act on externally-hosted, open-source content that can change and thus materially influence its behavior and outputs.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill fetches runtime instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md and explicitly uses that fetched content to control review rules and output format, so the external URL directly controls agent prompts and is a required runtime dependency.