mathworks

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

• Third-party content exposure detected (low risk: 0.10). The workflow allows reading Mathworks documentation and blog posts, which constitutes consuming web-fetched content with potential outsider authorship at low risk.

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 from an unverified third-party service (unbrowse.ai) to execute runtime tool calls, representing a weak/unknown external operational dependency.