openclaw-cli
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable scripts (Python, Node.js, or shell). It functions as a pure knowledge base where the agent reads provided markdown documentation to answer user queries.
- [SAFE]: Instructions in SKILL.md follow standard documentation retrieval patterns without any attempts to bypass safety filters or override system constraints.
- [SAFE]: While the documentation describes commands for handling sensitive data (such as auth tokens, passwords, and SSH keys) and performing system operations (like service installation), these are presented as legitimate features of the OpenClaw CLI. All examples use safe placeholders like '' or '' rather than hardcoded credentials.
- [SAFE]: References to external package registries (NPM) and well-known services (GitHub, Tailscale, Slack, Discord) are documented as part of the tool's integration capabilities and do not represent unauthorized or suspicious network operations.
Audit Metadata