hubspot

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

• Third-party content exposure detected (high risk: 0.75). At runtime the skill calls Apideck’s CRM unified API (and optionally the Proxy endpoint) to fetch HubSpot data; that fetched HubSpot content is outsider-authored free text (e.g., contact/company/deal fields) that the agent will ingest into the LLM context.