hubspot-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly calls HubSpot API endpoints (e.g., HUBSPOT_SEARCH_CONTACTS_BY_CRITERIA, HUBSPOT_GET_DEAL, HUBSPOT_SEARCH_TICKETS, HUBSPOT_READ_ALL_PROPERTIES_FOR_OBJECT_TYPE) to read CRM records and user-generated content from a HubSpot account, and that fetched content is used to drive decisions and subsequent tool actions (search-before-create, property mapping, pipeline/stage resolution) — exposing the agent to untrusted third-party content that could carry injected instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and calling the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly determine the agent's available tools/behavior, so this external URL can control prompts/instructions.