marketplace

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch and consume third‑party Marketplace and vendor content (e.g., "vercel integration discover", "vercel integration guide ", "vercel integration open " and curl queries to the /v1/drains API) and to read/interpret those returned integration/vendor setup steps and drain endpoints as part of its workflow, so untrusted provider-authored content can materially influence actions.