n8n-integration-testing-patterns

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md contains code that fetches and parses responses from public third‑party APIs (e.g., https://slack.com/api/auth.test, Google Sheets/Drive endpoints, SendGrid/Mailchimp/Airtable endpoints) and directly uses those responses to drive decisions and actions such as connectivity status, token refresh, retries, and rate‑limit behavior, which exposes the agent to untrusted third‑party content.