openclaw
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the OpenClaw platform from its official npm package and GitHub repository. These downloads are directed to the project's primary distribution channels for software setup and updates.
- [COMMAND_EXECUTION]: Provides detailed CLI commands for managing system-level services, including gateway initialization via launchd or systemd, and platform health diagnostics through the 'doctor' command. These operations are core to the platform's self-hosting functionality.
- [CREDENTIALS_UNSAFE]: Includes procedures for adding and managing API tokens for various messaging platforms like Telegram, Discord, and Slack, as well as AI providers like Anthropic. The platform manages these credentials locally within the user's workspace and includes a security audit feature to monitor for configuration risks.
- [COMMAND_EXECUTION]: Outlines capabilities for browser automation, allowing the agent to perform web-based tasks through controlled commands. This functionality is part of the tool's integrated automation suite.
Audit Metadata