n8n-workflow-patterns
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides educational examples for using n8n Code nodes to execute shell commands. For instance, in
scheduled_tasks.md, it demonstrates spawning a subprocess viachild_process.execto runpg_dumpfor database backups. - [PROMPT_INJECTION]: The skill describes patterns for AI agents that process external data, creating a potential surface for indirect prompt injection. Ingestion points: Webhooks receive data from external systems as documented in
webhook_processing.md. Boundary markers: Theai_agent_workflow.mdfile encourages structured system prompts and explicit guidelines to constrain AI behavior. Capability inventory: The documented patterns allow workflows to execute SQL queries, make HTTP requests, and run custom JavaScript or Python code. Sanitization: The skill provides significant remediation guidance, recommending parameterized queries, read-only database users, and manual validation code to mitigate injection risks. - [EXTERNAL_DOWNLOADS]: Describes patterns for integrating with external REST APIs using the HTTP Request node, including detailed guidance on secure authentication and rate-limiting.
Audit Metadata