follow-up-sequences

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

• Third-party content exposure detected (high risk: 0.70). The n8n workflow explicitly fetches interaction history from Attio and ingests inbound reply content from Smartlead webhooks (user-generated third‑party messages), and that content is fed into the AI message generation and sequence-status logic, so untrusted external inputs can influence actions.