n8n-subworkflows
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides best-practice guidance for n8n workflow development. It explicitly advises against insecure practices such as placing credentials in workflow inputs or returning them in outputs.
- [INDIRECT_PROMPT_INJECTION]: The skill describes mechanisms for exposing workflows as agent tools, which creates an inherent surface for processing external data. Ingestion points: Data enters the agent context through workflow triggers and tool return values. Boundary markers: The skill advocates for the 'Define Below' mode to establish clear schemas and typed inputs. Capability inventory: Referenced tools include workflow modification (n8n_update_partial_workflow), database management (n8n_manage_datatable), and execution inspection (n8n_executions). Sanitization: The guidance focuses on logical boundaries and credential safety, advising developers to avoid sensitive data in inputs.
Audit Metadata