secure-openclaw-ai-assistant

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

• Third-party content exposure detected (medium risk: 0.30). The workflow configures a messaging bot that processes incoming messages from chat and social platforms such as WhatsApp, Telegram, and Signal.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing a remote installation script from an unverified third-party domain (opencode.ai) during setup, presenting a weak-provenance operational dependency.