Audit installed skill permissions: detect network access, subprocess execution, file writes, unsafe deserialization, and environment variable usage. Permission matrix for every skill in your workspace. Free alert layer — upgrade to openclaw-arbiter-pro for revocation, quarantine, and policy enforcement.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install openclaw-arbiter或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install openclaw-arbiter⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/openclaw-arbiter/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: openclaw-arbiter user-invocable: true metadata: {"openclaw":{"emoji":"⚖️","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}} ---
Audits installed skills to report exactly what system resources each one accesses — network, subprocess, file I/O, environment variables, and unsafe operations.
You install skills and trust them blindly. A skill that claims to format markdown could also open network connections, execute shell commands, or read your environment variables. Nothing reports what permissions each skill actually uses.
Deep audit of all installed skills with line-level findings.
python3 {baseDir}/scripts/arbiter.py audit --workspace /path/to/workspace
python3 {baseDir}/scripts/arbiter.py audit openclaw-warden --workspace /path/to/workspace
Compact table showing permission categories per skill.
python3 {baseDir}/scripts/arbiter.py report --workspace /path/to/workspace
One-line summary of permission risk.
python3 {baseDir}/scripts/arbiter.py status --workspace /path/to/workspace
| Category | Risk | Examples | |----------|------|----------| | Serialization | CRITICAL | pickle, eval(), exec(), __import__ | | Subprocess | HIGH | subprocess, os.system, Popen, command substitution | | Network | HIGH | urllib, requests, curl, wget, hardcoded URLs | | File Write | MEDIUM | open('w'), shutil.copy, os.remove, rm | | Environment | MEDIUM | os.environ, os.getenv, os.putenv | | Crypto | LOW | hashlib, hmac, ssl | | File Read | LOW | open('r'), os.walk, glob |
0 — Clean, all skills within normal bounds1 — Elevated permissions detected (review needed)2 — Critical permissions detected (action needed)Python standard library only. No pip install. No network calls. Everything runs locally.
Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.
安装 Openclaw Arbiter 后,可以对 AI 说这些话来触发它
Help me get started with Openclaw Arbiter
Explains what Openclaw Arbiter does, walks through the setup, and runs a quick demo based on your current project
Use Openclaw Arbiter to audit installed skill permissions: detect network access, subproces...
Invokes Openclaw Arbiter with the right parameters and returns the result directly in the conversation
What can I do with Openclaw Arbiter in my ai agent & automation workflow?
Lists the top use cases for Openclaw Arbiter, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/openclaw-arbiter/ 目录(个人级,所有项目可用),或 .claude/skills/openclaw-arbiter/(项目级)。重启 AI 客户端后,用 /openclaw-arbiter 主动调用,或让 AI 根据上下文自动发现并使用。
Openclaw Arbiter 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Openclaw Arbiter 可免费安装使用。请查阅仓库了解许可证信息。
Audit installed skill permissions: detect network access, subprocess execution, file writes, unsafe deserialization, and environment variable usage. Permission matrix for every skill in your workspace. Free alert layer — upgrade to openclaw-arbiter-pro for revocation, quarantine, and policy enforcement.
Openclaw Arbiter 属于「AI Agent & Automation」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my ai agent & automation tasks using Openclaw Arbiter
Identifies repetitive steps in your workflow and sets up Openclaw Arbiter to handle them automatically