n8n-integration-testing-patterns

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md includes explicit runtime fetches of public third‑party APIs (e.g., https://slack.com/api/auth.test, Google Sheets values endpoints, genericAPIConnectivity and executeOperation for node-configured endpoints) and the agent is expected to read and act on those responses (scopes, token refresh, operation outcomes), so untrusted/user-generated content from those external sources can materially influence subsequent tool use and decisions.