npmjs

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

• Third-party content exposure detected (low risk: 0.10). The skill searches npmjs.com packages and registry data, which is an external public registry/package repository where anyone can publish content containing free text read by the agent (low risk).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to configure and connect an external Model Context Protocol (MCP) server hosted at unbrowse.ai, establishing an operational inbound dependency on a third-party service with common/reputable unofficial provenance.