security-investigator-automation

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow queries Microsoft Sentinel, Defender XDR, and Graph API logs, which contain security alerts, user activity, and threat telemetry that can include attacker-controlled inputs or strings.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning an external GitHub repository during setup, which constitutes an operational dependency from an unofficial repository.