ai-ecommerce-expert-tmall-ecommerce-content

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

• Third-party content exposure detected (medium risk: 0.30). 运行时的文本输入来自用户在调用 IMIVA MCP 工具（如 create_detail_page_task）时传入的 --args/extraDescription 字段，并作为 free text 由 LLM/模型使用处理后生成电商详情与素材（scripts/imiva_mcp.py 将这些参数直接发送给 @infimind/ecom-content-cli@latest）。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime invokes npx -y @infimind/ecom-content-cli@latest (seen in scripts/imiva_mcp.py and config), which fetches and executes remote npm package code during execution, so the package @infimind/ecom-content-cli@latest is a required runtime dependency that runs remote code.