aliyun-openclaw-setup

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill downloads and executes a setup script from NodeSource (https://deb.nodesource.com/setup_20.x) to install Node.js. NodeSource is a well-known service for Node.js distributions.
  • [EXTERNAL_DOWNLOADS]: The skill downloads plugins for the OpenClaw gateway from various sources, including NPM and an official GitHub repository for DingTalk integration (https://github.com/DingTalk-Real-AI/dingtalk-openclaw-connector.git). These downloads are necessary for the skill's primary functionality of adding messaging channels.
  • [COMMAND_EXECUTION]: The skill performs administrative tasks such as system package installation (apt-get), global NPM package installation, and service management using systemctl. These operations are performed with high privileges (often as root) which is appropriate for a system provisioning skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a workflow to "Auto-Discover" new channels by visiting the official documentation at https://docs.openclaw.ai/channels/index. While this involves processing external content, the risk is localized to the official documentation site of the software being installed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 08:16 AM