ai-ecommerce-expert-apparel-fashion-ecommerce-content

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

• Third-party content exposure detected (medium risk: 0.30). 运行时通过 IMIVA 的 MCP 工具 create_product_main_image_task 接收并处理用户在 Skill 中输入的自然语言需求与参数（如 coreSellingPoints、usageScenario 等），这些内容属于外部自由文本会被进入 LLM/工作流处理，而非先枚举固定项后再读取。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx to fetch and execute the npm package @infimind/ecom-content-cli@latest at runtime (e.g., subprocess.Popen([npx, "-y", "@infimind/ecom-content-cli@latest"])), which downloads and runs remote code and thus directly executes external content.