n8n AI Features

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

• Third-party content exposure detected (high risk: 0.90). The skill's Document Loading and RAG workflows explicitly ingest external content via HTTP requests and web downloads (e.g., "Document Loading" → [HTTP Request], "[HTTP: Get Topics]") and then feed that arbitrary third‑party/public content into retrievers/LLM chains for Q&A, exposing the agent to untrusted user-generated or public web content.