n8n-mcp-tools-expert
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of n8n node metadata, templates, and workflow configurations which act as external, potentially untrusted data sources.
- Ingestion points: Data enters the agent's context through tools like
search_nodes,get_node,get_template, andn8n_get_workflowas described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or protective prompt wrappers when the agent interprets the output from these tools.
- Capability inventory: The skill leverages powerful capabilities including
n8n_create_workflow,n8n_update_partial_workflow, andn8n_test_workflow, which allow for the creation, modification, and execution of logic on a remote n8n instance. - Sanitization: The skill mentions an "Auto-Sanitization" feature, but this is focused on fixing structural configuration errors (like operator types) rather than filtering for malicious instructions embedded in the data.
Audit Metadata