vercel-microfrontends

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs agents to fetch and parse live group/project data from Vercel (e.g., "vercel mf inspect-group --group="" --format=json" in references/managing-microfrontends.md and "vercel microfrontends pull" in references/local-development.md), which ingests untrusted third‑party project/config content that the agent is expected to interpret and use to generate configs or drive next actions.