aliyun-openclaw-setup

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow instructs the agent to open documentation URLs such as https://docs.openclaw.ai/channels/index to discover and extract channel information at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). An operational dependency on NodeSource is fetched via curl from deb.nodesource.com and executed during setup, representing a common unofficial or external setup script execution.