sequence-performance

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text is ingested in Step 1C “Reply Content” via the outreach tool’s reply history APIs (e.g., fetch_master_inbox_replies / get_campaign_lead_message_history), where reply_text contains messages written by recipients (not the operating user) and is then fed into Steps 3–6 for LLM analysis.