outlook

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow reads incoming email messages and messages from external senders via Outlook integration, exposing the agent to untrusted outsider-authored text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs execution of an external CLI package via npx from ClawLink, an unverified third-party service and registry locator, introducing a medium-tier operational dependency.