ai-ecommerce-expert-product-image-expansion

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 在用户提供的 tool parameters（如 create_image_expand_task 的 images/sellingPoints/targetAudience/usageScenario 等）被直接作为 MCP 调用参数发送给 @infimind/ecom-content-cli@latest，从而让外部作者的文本（用户输入）进入运行时工作流。

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 run the npm package "@infimind/ecom-content-cli@latest" at runtime (e.g., scripts/imiva_mcp.py), which executes remote code and is required for the MCP calls.