ezviz

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

• Third-party content exposure detected (low risk: 0.10). The workflow searches and reads pages from ezviz.com via Unbrowse MCP, exposing the agent to low-risk web content.

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 endpoint and REST API hosted by Unbrowse (unbrowse.ai), which supplies operational tools and behavior-governing instructions at runtime, constituting a common/reputable unofficial operational dependency.