1688-Product-to-Ozon

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires asking the user for API keys/secrets and shows config files and env var placements where those secrets must be filled, which encourages the LLM to receive and embed secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.30). 该技能在运行时会接收用户提供的“1688商品信息/图片URL/标题等”并将其中自由文本（如“商品简介/描述”“name”等）送入AI模型生成Ozon上架JSON，同时调用 translate_images.py 按这些图片URL向 AlphaShop 接口请求翻译，属于可被用户提交的文本注入面。