ai-ecommerce-expert-wechat-video-channel-ecommerce-content

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

• Third-party content exposure detected (medium risk: 0.30). At runtime the only outsider free text that can reach the LLM is the user-supplied prompt and related parameters passed into the IMIVA MCP tool via scripts/imiva_mcp.py (stdin JSON for tools/call create_video_generation_task), so the workflow ingests outsider-authored text directly for content generation without selecting a specific trusted item first.

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 run the npm package "@infimind/ecom-content-cli@latest" at runtime (e.g., subprocess [npx, "-y", PACKAGE]), which downloads and executes remote code required for operation.