phantom-ai-coworker

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors and consumes outsider-authored free text via Slack channels and direct messages where any user can send messages to the agent.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references GitHub-hosted configuration files and repository setup commands from an arbitrary personal user repository (ghostwright/phantom), which constitutes an unverified operational external dependency.