n8n-subworkflows
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes building sub-workflows that ingest data through Execute Workflow Triggers (SKILL.md, SUBWORKFLOW_PATTERNS.md). While it promotes the use of typed 'Define Below' triggers to create explicit schemas, these interfaces remain entry points for untrusted data that the agent may process.
- Ingestion points: Execute Workflow Trigger nodes, including both typed 'Define Below' and 'Passthrough' modes in SKILL.md and SUBWORKFLOW_PATTERNS.md.
- Boundary markers: The skill recommends explicit typed fields for schemas and 'Return' Set nodes to normalize output shapes, providing better structural boundaries than raw data flow (SKILL.md).
- Capability inventory: Workflows built using these patterns may perform database operations via n8n_manage_datatable, send notifications, or execute HTTP requests as documented in SKILL.md and SUBWORKFLOW_PATTERNS.md.
- Sanitization: The instructions point toward the n8n-validation-expert skill for validating inputs, but note that the platform does not automatically catch unrecognized fields (SKILL.md).
Audit Metadata