inbound-lead-triage

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

• Third-party content exposure detected (high risk: 0.78). Yes—Step 1 ingests outsider-authored free text such as “raw_message” from inbound leads (e.g., form messages, chat transcripts) and then Step 4/5 uses/quotes it in the LLM output (e.g., “Engagement: ‘[quote from form message or chat]’” and enrichment context), creating an indirect prompt-injection path from user-submitted content.