new-user-product-audit

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

• Third-party content exposure detected (medium risk: 0.30). The workflow requires registering for and receiving emails from a temporary inbox provider (mail.tm) via its API and reading the verification messages at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external public endpoints (mail.tm) as a standard operational dependency to dynamically provision temporary mailboxes and retrieve verification codes during agent execution.