alibaba

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

• Third-party content exposure detected (low risk: 0.10). The agent searches Alibaba.com products by keyword using Unbrowse tools, which returns third-party merchant content and product listings containing outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server and REST endpoints hosted on unbrowse.ai, which acts as a third-party gateway providing operational tool definitions and behavior-selecting configurations with common unofficial provenance.