n8n-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow patterns explicitly show ingesting untrusted external content (e.g., "Pattern 3: AI Agent" feeds webhook input via "={{ $json.body.message }}" into a LangChain AI agent, and other patterns use n8n httpRequest nodes to fetch external URLs), so third‑party/user‑provided content is read and can directly influence agent decisions and downstream tool actions.