using-n8n-mcp-skills
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from potentially untrusted external sources (n8n instances) via tools like
get_node,n8n_get_workflow, andsearch_templates, creating a vulnerability surface where malicious instructions could be embedded in node metadata or workflow configurations. - Ingestion points: Tool outputs from
get_node,n8n_get_workflow,search_nodes, andsearch_templates(found in SKILL.md). - Boundary markers: The skill does not define explicit delimiters or instruction-ignore blocks to separate external tool data from the agent's internal control logic.
- Capability inventory: The skill provides guidance on using powerful tools including
n8n_update_partial_workflow,n8n_manage_credentials, andn8n_manage_datatable(found in SKILL.md). - Sanitization: While the skill contains strong operational security advice (e.g., regarding credential handling), it does not provide mechanisms for sanitizing or escaping the content of retrieved workflows before they are processed by the agent.
Audit Metadata