hubspot-automation
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from HubSpot CRM and uses it to perform automated actions, including write operations. Malicious data within the CRM could potentially override agent instructions. Ingestion points: Data retrieved via tools like HUBSPOT_SEARCH_CONTACTS_BY_CRITERIA, HUBSPOT_SEARCH_DEALS, and HUBSPOT_GET_TICKET. Boundary markers: Absent; instructions do not include delimiters or warnings to treat external data as untrusted. Capability inventory: Includes record creation and update tools such as HUBSPOT_CREATE_CONTACTS and HUBSPOT_UPDATE_COMPANIES. Sanitization: No explicit sanitization or validation of CRM content is mentioned in the workflow instructions.
- [EXTERNAL_DOWNLOADS]: The skill requires the user to configure an external MCP server at https://rube.app/mcp to provide tool schemas and enable functionality.
Audit Metadata