happy-horse-reference-to-video

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

• Third-party content exposure detected (medium risk: 0.30). The runtime ingests outsider-provided free text from the CLI --prompt (and optional --system) and sends it as the messages/prompt fields to the AI Hive /openapi/v1/chat/text and /openapi/v1/generation/video endpoints via scripts/videogen.py → skill_main() → skill_generate() → cmd_video() → client.generate_video() / client.chat_text().