make-bot-ui

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

• Third-party content exposure detected (medium risk: 0.30). The webhook routine consumes incoming POST bodies from external users over a webhook, which constitutes an outsider-submitted free text source handled by the agent.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill downloads and executes an installation script from https://tailscale.com/install.sh at runtime via curl piped to sh.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs the agent to execute commands using sudo to install and configure Tailscale, which violates the security policy regarding obtaining root privileges and modifying system state.