ai-ecommerce-expert-horizontal-16-9-tvc

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

• Third-party content exposure detected (medium risk: 0.30). Skill 的运行路径主要是将用户提供的素材/卖点等被用户作者化的 prompt 作为参数传入 IMIVA MCP 工具 create_video_generation_task（通过 agents/openai.yaml 的默认提示与 scripts/imiva_mcp.py 的 tools/call/method 调用），属于外部任意文本进入模型并影响下游生成流程的间接提示注入暴露。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime script invokes npx to fetch and execute the remote npm package "@infimind/ecom-content-cli@latest" (via subprocess), which downloads and runs remote code as a required dependency.