product-video

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path scripts/videogen.py in skill_generate forwards outsider-authored --prompt (and optional --system) from the user directly into the OpenAPI call AiHiveClient.chat_text(...)->POST /openapi/v1/chat/text or AiHiveClient.generate_video(...)->POST /openapi/v1/generation/video, meaning arbitrary free text submitted by the user is ingested by the LLM without selecting a specific item.