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 allows AI agents to call arbitrary external sources (see ai_agent_workflow.md: HTTP Request tool, Serper/Google search, Wikipedia tool, GitHub issue searches and "ANY node can be an AI tool") and the HTTP API Integration and Webhook patterns describe fetching and ingesting data from public APIs and webhooks, meaning the agent will read untrusted, user-generated or public web content as part of its workflow.