using-n8n-mcp-skills

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides architectural guidance and emphasizes secure workflow design. It explicitly instructs the agent to avoid hardcoding secrets in text fields and mandates human-in-the-loop confirmation before executing workflows that may have side effects.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external workflow definitions and tool documentation from an n8n instance, creating a potential surface for indirect prompt injection via malicious workflow metadata or comments.
  • Ingestion points: External workflow data is ingested via n8n_get_workflow, tools_documentation, and template search tools.
  • Boundary markers: The skill does not define specific prompt delimiters but mandates the use of validate_workflow and manual connection verification to mitigate risks.
  • Capability inventory: The toolset includes capabilities for modifying workflows (n8n_update_partial_workflow), managing credentials (n8n_manage_credentials), and remote execution (n8n_test_workflow).
  • Sanitization: There are no specific instructions for filtering or sanitizing strings ingested from the n8n API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:56 AM
Security Audit — agent-trust-hub — using-n8n-mcp-skills