milelion

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and reads pages from a specific website (milelion.com) via search and page-reading tools, which constitutes fetching external content under the low-risk category.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill configures a remote Model Context Protocol (MCP) server at https://unbrowse.ai/mcp/milelion.com, establishing an operational dependency on a third-party unofficial service with unknown publisher provenance.