using-n8n-mcp-skills

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves ingesting data from external n8n instances which could contain embedded malicious instructions.
  • Ingestion points: Data enters the context via get_node, n8n_get_workflow, and search_nodes as listed in SKILL.md.
  • Boundary markers: The skill does not define delimiters for external data or instruct the agent to ignore embedded commands.
  • Capability inventory: The skill facilitates access to high-privilege tools such as n8n_create_workflow, n8n_update_partial_workflow, n8n_manage_credentials, and n8n_test_workflow.
  • Sanitization: While validation is recommended for structure, there is no explicit sanitization for natural language prompt injection within the workflow JSON.
  • [SAFE]: The skill mandates a 'Non-negotiable' rule that prohibits hardcoding secrets in text fields, ensuring they are managed via n8n's secure credential system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:10 PM
Security Audit — agent-trust-hub — using-n8n-mcp-skills