happy-horse-ai-ad-video

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text from the CLI argument --prompt (and optionally --system) and forwards it as messages[].content into AiHiveClient.chat_text(...) via the generate → skill_generate → cmd_video → client.generate_video path.