ai-ecommerce-expert-promotion-poster

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

• Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the user-provided free text fields (e.g., the prompt passed to create_smart_refine_task for “电商促销海报”) are directly ingested by the MCP call without any prior selection of a specific trusted item.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill spawns npx to fetch and run the remote npm package "@infimind/ecom-content-cli@latest" at runtime (see scripts/imiva_mcp.py invoking npx and the mcp config), which causes remote code to be downloaded and executed.