n8n-workflow-patterns

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Yes — a Google Drive uc?export=download link can host any file (including executables) from personal accounts and is commonly used to distribute malware or obscure origin, so it should be treated as high risk unless the sender and file are verified.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs agents to fetch and process open/public third‑party content (e.g., HTTP Request calls, Serper/Wikipedia/GitHub searches, document loaders and web scrapers) as part of AI Agent and HTTP API workflows (see ai_agent_workflow.md and http_api_integration.md), and those fetched, untrusted results are used to decide tool calls and actions—creating a clear indirect prompt‑injection exposure.