ai-ecommerce-expert-reference-style-main-image

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

• Third-party content exposure detected (medium risk: 0.30). 该技能运行时通过脚本 scripts/imiva_mcp.py 调用 IMIVA MCP 工具（如 create_product_main_image_task），其可读输入主要来自用户提供的 --args/--args-file JSON（包含商品卖点、场景等自由文本），因此存在被用户/外部提交的提示注入文本进入运行流的间接风险。

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 remote npm package "@infimind/ecom-content-cli@latest" at runtime (scripts/imiva_mcp.py invokes [npx, "-y", PACKAGE]), which is a required runtime dependency that executes remote code.