hubspot-automation

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure a remote MCP server at https://rube.app/mcp. This connects the agent to a third-party execution environment that mediates access between the agent and the HubSpot CRM.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from HubSpot CRM, which is a significant surface for indirect injection attacks.
  • Ingestion points: Data enters the agent's context through tools like HUBSPOT_SEARCH_CONTACTS_BY_CRITERIA, HUBSPOT_GET_COMPANY, HUBSPOT_SEARCH_TICKETS, and HUBSPOT_RETRIEVE_OWNERS (found in SKILL.md).
  • Boundary markers: Absent. The instructions do not provide delimiters or specific guidance to the agent to ignore potentially malicious instructions embedded in contact fields, ticket descriptions, or deal notes.
  • Capability inventory: The skill possesses extensive write capabilities, including creating/updating contacts, companies, deals, and custom properties (e.g., HUBSPOT_CREATE_CONTACT, HUBSPOT_CREATE_COMPANIES, HUBSPOT_CREATE_PROPERTY_FOR_SPECIFIED_OBJECT_TYPE), which could be abused if the agent follows instructions hidden in processed data.
  • Sanitization: Absent. There are no instructions for the agent to validate or sanitize external content before interpolation or action.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:34 PM
Security Audit — agent-trust-hub — hubspot-automation