n8n-workflow-sdk

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows runtime httpRequest and webhook usage that ingests external, potentially untrusted third‑party content (e.g., httpRequest calls to https://api.example.com, Mailchimp, Clearbit and the webhook-triggered AI agent in "AI Support Agent") and then uses those responses inside an AI/langchain node to make decisions, so third‑party content can materially influence tool use and agent behavior.