make-bot-ui

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

• Third-party content exposure detected (medium risk: 0.30). The workflow sets up a webhook task that ingests external HTTP requests sent by users or third parties interacting with the custom UI.

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 install and configure Tailscale using sudo privileges if it is not already installed, which compromises the machine state.