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 monitors a webhook endpoint that receives untrusted POST bodies from external clients, which are ingested during webhook wake turns.

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 scripts and commands using sudo to install and configure Tailscale, which violates security policies against obtaining or using elevated privileges.