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 ingests POST bodies from an external source (the user-created bot UI page) which can contain outsider-authored free text.

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 (curl ... | sudo sh and sudo tailscale up), which compromises the machine's state by asking the agent to obtain sudo privileges.