ai-ecommerce-expert-audio-reference-video

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

• Third-party content exposure detected (medium risk: 0.30). 工作流通过 IMIVA MCP 工具 create_video_generation_task 在用户提供的 prompt/referenceAudios 等参数上执行（见 SKILL.md 的“预检/正式生成”调用示例），因此会把外部用户自由文本直接送入运行时生成任务。

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 npm package "@infimind/ecom-content-cli@latest" at runtime (scripts/imiva_mcp.py calls subprocess.Popen([npx, "-y", PACKAGE], ...)), so remote code is fetched and executed as a required dependency.