ai-agent-sla-and-customer-commitments

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly includes runtime loading of remote assets that execute code in host pages (notably the JS SDK URL https://app.example.com/sdk/sla-widget.js and the iframe source https://app.example.com/sla/widget?token=...), so these are runtime external dependencies that fetch and execute remote code.