bknd-custom-endpoint

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

• Third-party content exposure detected (high risk: 1.00). The skill shows runtime ingestion of untrusted third‑party content — e.g., FetchTask calling external URLs (url: "https://api.example.com/data") and multiple webhook/plugin routes that parse and return arbitrary request bodies (e.g., /api/webhooks/stripe, /api/webhooks/github, and the /api/custom/echo route) — meaning the agent will read and act on user-generated/open web content.