account-tier-scoring

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests and scores account signal events (e.g., chat/support interactions, meetings, outreach replies, website visit/context, and LinkedIn engagement) and then extracts “what did they ask?” / “questions” / “topics, objections” from those payloads at Steps 3 and the intent/trial references, which are outsider-authored free text.