debug

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow (“Debugging by tool” / “Lovable / Replit (founder pastes into chat)”) ingests outsider-authored free text from the founder’s chat messages via the “Tell AI:” prompts, e.g., the user supplies bug descriptions, console/network errors, and screenshots text in chat that the LLM then processes.