hubspot

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow can call HubSpot actions (e.g., account-deep-dive, hubspot-records, hubspot-deals, or provider-api-request) that ingest CRM record fields and free-text notes/emails from other people into the LLM context, which is outsider-authored content (even if stored in the user’s HubSpot tenant).