Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jd-opensource/JoySafeter --skill openclaw-security-checkergit clone --depth 1 https://github.com/jd-opensource/JoySafeterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jd-opensource/joysafeter/openclaw-security-checker)<a href="https://agentmods.dev/skills/jd-opensource/joysafeter/openclaw-security-checker"><img src="https://agentmods.dev/badge/skills/jd-opensource/joysafeter/openclaw-security-checker.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.02213 |
| Opus 5 | $0.00019 | $0.01107 |
| Sonnet 5 | $0.00008 | $0.00443 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
openclaw-security-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw 安全检测器
基于《OpenClaw 极简安全实践指南》和《安全验证与攻防演练手册》的全面安全检测工具。对 OpenClaw 实例的配置、权限、隔离、网络、日志进行系统化审查，输出可量化的安全评分和修复建议。
Purpose
OpenClaw 实例运行在 Docker 容器中，每用户独占一个容器（JoySafeter 架构）。该技能负责对实例的安全面进行系统化检测，覆盖部署前配置审查、运行时权限验证、隔离区合规检查三个阶段。
Prerequisites
环境要求
- OpenClaw 实例已部署并可访问（本地或容器内）
- 对
~/.openclaw/目录有读取权限 openclaw.json配置文件可读
目标实例信息
- OpenClaw 版本号（
openclaw --version） - 部署模式：local / docker / kubernetes
- Gateway 端口和绑定范围
Core Workflow
- 配置文件扫描: 解析
openclaw.json，检查 gateway 认证、绑定范围、工具权限、模型配置中的安全隐患。 - 凭证暴露检测: 扫描配置文件、环境变量、日志中是否存在明文 API Key、Token、密码。
- Gateway 安全审计: 验证 gateway 绑定地址、认证方式、CORS 白名单、trusted proxies 配置。
- 工具权限验证: 检查
tools.profile设置，验证文件系统访问范围、命令执行权限、网络访问策略。 - 文件权限检查: 验证
~/.openclaw/目录及关键文件的权限位，确保配置文件不可被其他用户读取。 - 隔离区合规检查: 扫描
_quarantine目录，列出被隔离的技能及原因，验证隔离机制是否正常运作。 - 运行时完整性验证: 通过 SHA-256 哈希校验核心文件完整性，对比安装时的基线值。
- 日志审计分析: 检查最近操作日志中的可疑模式（大量失败请求、敏感操作、红线触发记录）。
- 网络策略检查: 验证出站网络请求白名单、DNS 解析范围、容器网络隔离状态。
检查项目详情
1. 配置安全检查
| 检查项 | 风险等级 | 检测规则 | 扣分 |
|---|---|---|---|
| API Key 明文暴露 | CRITICAL | 正则匹配 sk-*, key-*, token: 等模式 |
-20 |
| Gateway 绑定 0.0.0.0 | HIGH | 检查 gateway.bind 是否为 0.0.0.0 或 lan |
-10 |
| 工具权限设为 full | MEDIUM | tools.profile === "full" |
-5 |
| CORS 白名单过宽 | MEDIUM | allowedOrigins 包含 * |
-5 |
| 认证 Token 弱强度 | HIGH | Token 长度 < 32 或 entropy < 4.0 | -10 |
| 禁用设备认证 | HIGH | dangerouslyDisableDeviceAuth: true |
-10 |
| 模型 context 过大 | LOW | contextWindow > 200000 |
-2 |
| 未配置 TLS | MEDIUM | Gateway 未启用 HTTPS | -5 |
| 自动更新已禁用 | LOW | update.checkOnStart: false |
-3 |
2. 权限与隔离检查
| 检查项 | 风险等级 | 检测规则 | 扣分 |
|---|---|---|---|
| 配置文件权限过宽 | HIGH | openclaw.json 权限非 600/640 |
-10 |
| 工作区目录权限 | MEDIUM | /workspace/ 权限非 700/750 |
-5 |
| 以 root 运行 | CRITICAL | 当前进程 UID == 0 | -20 |
| 文件系统未限制 | HIGH | tools.fs.workspaceOnly: false |
-10 |
| 隔离区异常 | MEDIUM | _quarantine 中存在未审查的技能 |
-5 |
3. 网络安全检查
| 检查项 | 风险等级 | 检测规则 | 扣分 |
|---|---|---|---|
| trusted proxies 过宽 | MEDIUM | 包含 /8 大段网络 |
-5 |
| 出站无白名单 | HIGH | 未配置出站网络限制 | -10 |
| Gateway 暴露在公网 | CRITICAL | 端口可从容器外访问 | -15 |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 175 lines · 39 tokens per session scan A c820db94455c
openclaw-security-checker is a skill published in the GitHub repository jd-opensource/JoySafeter (306 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 2,213 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
xhs_note
A workflow for creating a Xiaohongshu post, a Chinese image-first social-media note, with short copy, hashtags, and at least three matching vertical images.
dingtalk_channel_connect
A browser-based setup guide for connecting a MateClaw assistant to DingTalk, a Chinese workplace messaging platform. It creates and configures a DingTalk application, then publishes the configuration.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…