python

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and retrieves documentation from python.org via Unbrowse MCP, which is considered searching public documentation and external web content (low risk under the scoring rules).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to connect a remote third-party Model Context Protocol (MCP) server hosted at unbrowse.ai, which provides executable instructions and runtime tool behavior via an unverified third-party service, constituting a weak/unknown operational dependency.