n8n

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly defines a Webhook node that accepts external HTTP POSTs (http://localhost:5678/webhook/...) and an HTTP Request node calling external URLs (e.g., https://api.example.com/endpoint), and shows using incoming/remote JSON (={{ $json }}, {{ $json.status }}) to drive IF branching and other workflow actions, so untrusted third-party content is ingested and can materially influence behavior.