skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/n8n-workflow-automation/Gen Agent Trust Hub
n8n-workflow-automation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides examples of using n8n's executeCommand node to run shell commands, such as executing a Python script for IFC data extraction.
- [DYNAMIC_EXECUTION]: The skill utilizes n8n Code nodes to execute custom JavaScript and Python logic for processing BIM data and generating reports.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Untrusted data enters the workflow via localFileTrigger (watching Revit and IFC directories) and httpRequest nodes (fetching data from Project and Weather APIs).
- Boundary markers: The provided examples do not implement explicit delimiters or boundary markers for the processed file content.
- Capability inventory: The workflow has access to shell command execution, custom script execution, database interactions (PostgreSQL), and network operations.
- Sanitization: While best practices are mentioned in the documentation, the code examples do not show explicit sanitization of input variables such as file paths or external data strings.
Audit Metadata