n8n-workflow-architect
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze business stacks and integration requirements involving various external SaaS platforms (e.g., Shopify, HubSpot, Zendesk). This creates a surface where data ingested from these platforms could potentially contain malicious instructions intended to influence the agent's architectural decisions or tool handoffs.
- Ingestion points: Descriptions of business stacks and integration points provided by users or retrieved via n8n MCP tools (
search_nodes,get_node_documentation). - Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to separate untrusted system data from agent instructions.
- Capability inventory: The skill utilizes n8n MCP tools for node discovery and workflow creation, and coordinates with other skills capable of executing JavaScript and Python code.
- Sanitization: The instructions recommend that users implement validation in their production workflows, but do not provide specific sanitization or escaping guidelines for the agent when processing external stack information.
Audit Metadata