vercel-skill

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md and references explicitly list web_fetch_vercel_url and get_access_to_vercel_url plus toolbar/thread and runtime-log endpoints (e.g., "Protected previews: get_access_to_vercel_url, web_fetch_vercel_url" and "list_toolbar_threads/get_toolbar_thread") which cause the agent to fetch and read Vercel-hosted, user-generated pages, previews, logs, and threads (untrusted third‑party content) that can influence decisions and actions.