mariadb

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 mariadb.org via Unbrowse's MCP server, which exposes public documentation and web content that the agent actively fetches.

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 server hosted at unbrowse.ai, which provides executable tool definitions and behavior-selecting configuration for interacting with mariadb.org through an unofficial third-party service, representing a medium-tier common/reputable unofficial operational dependency.