n8n-mcp-setup

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs connecting Claude Code to external services via the n8n-MCP server (see "When to Use
• Connecting Claude Code to external services (Slack, email, CRMs, databases)" and the n8n API configuration), which means the agent will ingest and act on untrusted, user-generated third-party content from those integrations through n8n.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill requires running the n8n-mcp package at runtime (e.g., "npx n8n-mcp" / Docker image czlonkowski/n8n-mcp) which fetches and executes remote code from the n8n-mcp project (github.com/czlonkowski/n8n-mcp), so external code is executed as a required runtime dependency.