n8n-crm-automation

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

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs calling ColdIQ via an HTTP Request node (outsider-provided API responses at https://api.coldiq.com and/or ColdIQ MCP endpoint), and those HTTP/MCP response texts can be injected into the agent/LLM context when used for enrichment/scoring before CRM updates.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running a runtime npx command that fetches and executes remote code ("COLDIQ_API_KEY= npx -y @coldiq/mcp@latest"), so the package @coldiq/mcp downloaded at runtime can execute code and is a required dependency.