conversation-ng

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow is to read and use the full chat history (including the other person’s messages) to generate a reply, so at runtime it will ingest outsider-authored free text from the conversation itself (e.g., WhatsApp/DM messages written by the other participant).