sales-instantly

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

• Third-party content exposure detected (high risk: 0.72). Outsider free text can enter the LLM via the reply_received webhook payload (e.g., email subject/body/from/to) that Instantly POSTs to the agent’s endpoint, and the agent may include that webhook content in its LLM context—this is outsider-authored message content from third parties replying to the user’s emails.