n8n-workflow-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to fetch and ingest open/public third-party content—e.g., ai_agent_workflow.md shows AI Agents calling HTTP Request tools and web/document search tools (example: search_github_issues calling https://api.github.com/search/issues) and webhook_processing.md/http_api_integration.md describe receiving and fetching arbitrary external API/web content—which the agent is expected to read and use to choose tool calls and subsequent actions, creating a clear vector for indirect prompt injection.