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 whose incoming JSON payload from outsider-facing UI requests is rendered via placeholders and ingested as runtime prompt content.

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 commands if it is not already installed on the machine.