n8n-mcp-tools-expert

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of documentation in Markdown format and does not include any executable scripts, binary files, or hardcoded credentials.- [PROMPT_INJECTION]: The skill identifies a surface for Indirect Prompt Injection. It documents tools that fetch external data which could influence agent behavior.
  • Ingestion points: The tools search_templates and get_template retrieve user-generated content from the external n8n template library (referenced in SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided in the guidance for processing external templates.
  • Capability inventory: The skill describes high-privilege operations such as n8n_create_workflow and n8n_update_partial_workflow (documented in SKILL.md) which allow the modification of workflow logic and execution of code nodes.
  • Sanitization: While the guide mentions an internal 'Auto-sanitization system' for node structural integrity, there is no mention of sanitization or validation for natural language instructions or scripts contained within external templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:09 PM