n8n-crm-automation
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends using
npx -y @coldiq/mcp@latestto connect a Model Context Protocol server. This involves downloading a package from the npm registry at runtime. - [REMOTE_CODE_EXECUTION]: The instruction to run
@coldiq/mcpvianpxleads to the execution of remote code. As this package is owned by the skill's author ('cold-iq'), it is considered a vendor-provided tool for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external CRM systems like HubSpot and Salesforce (e.g., 'Lead routing', 'Deal stage alerts'). Data from these third-party platforms enters the agent's context and could potentially contain malicious instructions.
- Ingestion points: CRM triggers and search results from HubSpot and Salesforce.
- Boundary markers: No specific delimiters or safety instructions are provided to distinguish between CRM data and system instructions.
- Capability inventory: The skill uses network operations (HTTP Request nodes) and shell commands (
npx). - Sanitization: No explicit sanitization or validation of CRM data is described in the provided workflow patterns.
Audit Metadata