ai-ecommerce-expert-new-product-launch-content

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

• Third-party content exposure detected (medium risk: 0.30). 该 Skill 的运行时通过脚本 scripts/imiva_mcp.py 调用 IMIVA MCP 工具（如 create_product_main_image_task）并读取/处理由用户在 --args 中提供的自由文本字段（如 coreSellingPoints、generationStyle、usageScenario 等），因此外部任意文本会在未先选择特定“条目/来源”的情况下直接进入 LLM/MCP 参数链路。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill launches npx to fetch and execute the remote npm package "@infimind/ecom-content-cli@latest" at runtime (and uses https://imiva.ecpro.com as the MCP endpoint), meaning remote code is retrieved and executed as a required dependency.