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 shanggqm/openclaw-security-hardening --skill guomeiqing-security-auditgit clone --depth 1 https://github.com/shanggqm/openclaw-security-hardeningWrote 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/shanggqm/openclaw-security-hardening/guomeiqing-security-audit)<a href="https://agentmods.dev/skills/shanggqm/openclaw-security-hardening/guomeiqing-security-audit"><img src="https://agentmods.dev/badge/skills/shanggqm/openclaw-security-hardening/guomeiqing-security-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shanggqm/openclaw-security-hardening/guomeiqing-security-audit"><img src="https://agentmods.dev/badge/skills/shanggqm/openclaw-security-hardening/guomeiqing-security-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00063 | $0.04991 |
| Opus 5 | $0.00032 | $0.02495 |
| Sonnet 5 | $0.00013 | $0.00998 |
| Haiku 4.5 | $0.00006 | $0.00499 |
Grade B, and why
guomeiqing-security-audit scanned grade B with 2 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 12d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- 命令: `chmod 700 ~/.openclaw && chmod 600 ~/.openclaw/openclaw.json` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**WARN 影响说明:** 没有沙箱意味着 Agent 执行代码时直接操作宿主文件系统,一次错误的 `rm -rf` 就可能造成不可逆损失。沙箱可以将 Agent 限制在隔离环境中。 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🦞🔒 OpenClaw Security Hardening
你是一个安全审计专家。用户触发了安全检查,你需要按以下流程逐步执行:扫描 → 报告 → 方案 → 执行。
Step 1: 扫描配置
1.1 读取配置文件
执行以下命令获取配置和文件权限信息:
用 read 工具读取 ~/.openclaw/openclaw.json(路径通常是 /data/.openclaw/openclaw.json 或 $HOME/.openclaw/openclaw.json)
用 exec 工具执行: stat -c '%a %U:%G' ~/.openclaw ~/.openclaw/openclaw.json
将读取到的 JSON 解析为配置对象 config,用于后续所有检查。
1.2 逐项审计
对以下 7 个检查项逐一评估,每项判定为 PASS、WARN 或 FAIL:
检查项 1: DM 策略(🔴 极高风险 · 权重 20 分)
检查路径: config.channels.*
判断逻辑:
- 遍历
config.channels下的每一个渠道(如telegram、discord、feishu、slack等) - 对每个渠道,检查
dmPolicy字段:- 如果
dmPolicy为"open"→ FAIL(任何人都能私聊你的龙虾,极度危险) - 如果
dmPolicy为"pairing"→ WARN(配对制,首次需确认,基本安全但非最严格) - 如果
dmPolicy为"allowlist"且allowFrom数组非空 → PASS - 如果
dmPolicy缺失或为其他值 → WARN(无法确认安全性)
- 如果
综合判定:
- 任意一个渠道 FAIL → 整项 FAIL
- 无 FAIL 但有 WARN → 整项 WARN
- 全部 PASS → 整项 PASS
FAIL 影响说明: dmPolicy: open 意味着互联网上任何人都可以向你的 Agent 发送消息并获得回复。如果 Agent 还有工具权限(如 exec、read/write),攻击者可以读取你的文件、执行命令、窃取 API Key。这是最严重的安全风险。
检查项 2: Gateway 网络暴露(🔴 极高风险 · 权重 20 分)
检查路径: config.gateway
判断逻辑:
(a) 绑定地址检查:
- 读取
config.gateway.bind- 如果值为
"lan"或"0.0.0.0"→ FAIL(暴露到局域网或公网) - 如果值为
"loopback"或"127.0.0.1"或"localhost"→ PASS - 如果字段缺失 → WARN(取决于默认值,需确认)
- 如果值为
(b) Auth 认证检查:
- 读取
config.gateway.auth- 如果
auth.mode为"none"或auth字段不存在 → FAIL(无认证保护) - 如果
auth.mode为"token"→ 检查是否有实际配置的 token(有 → PASS,无法确认 → WARN) - 如果
auth.mode为其他认证方式 → PASS
- 如果
(c) Control UI 检查:
- 读取
config.gateway.controlUi- 如果
dangerouslyDisableDeviceAuth为true→ WARN(绕过了设备认证) - 如果
dangerouslyAllowHostHeaderOriginFallback为true→ WARN - 如果
allowInsecureAuth为true→ WARN
- 如果
综合判定:
- bind 非 loopback 且 auth 为 none → FAIL(裸奔暴露)
- bind 非 loopback 但 auth 有 token → WARN(有认证但网络暴露)
- bind 为 loopback → 即使 auth 较弱也至少 WARN
- bind 为 loopback 且 auth 有效 且 controlUi 无危险选项 → PASS
What ships with it
3 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.
- 12d ago First seen · 450 lines · 63 tokens per session scan B 827cd552e54b
guomeiqing-security-audit is a skill published in the GitHub repository shanggqm/openclaw-security-hardening (52 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 4,991 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…