n8n-workflow-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted third‑party content: webhook_processing.md describes receiving arbitrary webhook payloads ($json.body), http_api_integration.md shows HTTP Request nodes calling external APIs, and ai_agent_workflow.md allows the AI Agent to call HTTP Request / Serper / Wikipedia / search tools (ai_tool) and consume their results—so the agent is expected to read and interpret open web or user-generated content as part of its workflow.