n8n-workflow-patterns

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

• Third-party content exposure detected (high risk: 0.90). The ai_agent_workflow.md and related pattern files explicitly show the agent connecting to HTTP Request tools, web searches (Serper/Wikipedia), document loaders/vector stores, and webhooks (e.g., "HTTP Request Tool", "Search GitHub issues", "Serper Tool", "Webhook → AI Agent"), meaning the agent will fetch and ingest arbitrary public/user-generated web content and then use those results to decide tool calls and subsequent actions—exposing it to untrusted third‑party content that could supply indirect instructions.