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's workflow explicitly requires fetching and applying rules from a public third‑party URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md), meaning the agent will read and act on untrusted external content that can alter its decisions and outputs.

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 instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md via WebFetch and applies those fetched rules to control the agent's prompts and outputs, so this external URL directly controls agent behavior at runtime.