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 processes incoming POST requests from external users via a webhook, ingesting outsider-authored free text in the request body.

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 Tailscale and bring up the node using sudo, which violates the security policy against asking the agent to obtain sudo privileges or run commands requiring sudo.