openclaw-multi-channel-ai-assistant

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

• Third-party content exposure detected (medium risk: 0.30). The skill configures a multi-channel AI assistant gateway that receives messages and webhooks from chat platforms (WhatsApp, Telegram, Discord) and external services (GitHub), which can ingest outsider-authored free text into the agent workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions use an unauthenticated shell execution via curl from 'https://get.openclaw.ai' to install the platform, representing a weak, arbitrary external runtime dependency.