ai-ecommerce-expert-instagram-ecommerce-content

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

• Third-party content exposure detected (medium risk: 0.30). 运行时通过脚本 scripts/imiva_mcp.py 调用 IMIVA MCP 工具（如 create_koc_note_package_task/get_user_tasks），接收并处理由用户填写的自由文本参数（如 productName、sellingPoints、targetAudience、usageScenario 等）后再提交给 MCP，而该流程不体现对用户文本的“必须先选择具体来源项/主动搜索特定外部内容”的限制。

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes npx to fetch and run the npm package "@infimind/ecom-content-cli@latest" at runtime (see scripts/imiva_mcp.py and config examples), which downloads and executes remote code from the registry.