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 task ingests arbitrary outsider-submitted JSON bodies and request headers from incoming HTTP requests sent by users via custom UI pages.

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 prompt instructs the agent to run installation and setup commands using sudo for Tailscale, which violates the security policy against asking the agent to obtain sudo privileges or bypass security mechanisms.