Agent skill

Security Guide

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

Apache-2.0Auto-check: warningsSecurity

Install Security Guide

The automated check flagged lines worth reading first. See the safety section below.

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/security-guide .claude/skills/security-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .claude/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/security-guide .agents/skills/security-guide && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .agents/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/security-guide .cursor/skills/security-guide && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .cursor/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/jnMetaCode/shellward.git --path skills/security-guide

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/security-guide .gemini/skills/security-guide && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .gemini/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/security-guide .github/skills/security-guide && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .github/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add jnMetaCode/shellward --skill security-guide -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install jnMetaCode/shellward security-guide --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/security-guide .opencode/skills/security-guide && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "security-guide" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/security-guide into .opencode/skills/security-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-guide", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: security-guide
GitHub stars: 140
Token cost: ~644 tokens
SKILL.md length: 292 words
Files: 1
Skills in repo: 2
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

Works in 6 steps: Network Control / 网络控制 → Container Isolation / 容器隔离 → Credential Management / 凭证管理 → …
Tasks that involve Prompt injection and agent security
SKILL.md covers Security Checklist, Available Commands and Response Style
Calls docker

What it does

Security Guide is an agent skill from jnMetaCode/shellward. OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Prompt injection and agent security, Deployment and LLM guardrails. It works with Model Context Protocol and LangChain. The repository describes itself as: AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Prompt injection and agent security
Tasks that involve Deployment
Tasks that involve LLM guardrails

Example prompts

“/security-guide”

Requirements

Node.js
Docker

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Network Control / 网络控制
Container Isolation / 容器隔离
Credential Management / 凭证管理
Audit Logging / 审计日志
Plugin Security / 插件安全
Patch Management / 补丁管理

What it can do on your machine

Read from SKILL.md and the folder at commit 78444dd. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- docker
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Security Guide loads about 644 tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 292 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~27
When it runs · the whole SKILL.md, loaded when a task matches: ~644

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

NoteMentions a .env fileSKILL.md:32

- Scan for plaintext secrets in .env, .bashrc, environment variables

WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:35
```
- Suggest `chmod 600 ~/.env ~/.ssh/* ~/.aws/credentials`
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jnMetaCode/shellward at commit 78444dd, republished under its Apache-2.0 licence (© jnMetaCode). 292 words, ~644 tokens.

Download SKILL.mdSave it as .claude/skills/security-guide/SKILL.md (or your agent's skills folder).

name: security-guide
description: OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation
user-invocable: true
disable-model-invocation: false

ShellWard Security Deployment Guide / 安全部署指南

When the user invokes this skill, provide a complete security deployment checklist based on the following best practices. Check the current system state using available tools and give actionable recommendations.

Security Checklist

1. Network Control / 网络控制

Check if OpenClaw gateway port (19000/19001) is exposed to public network
Recommend binding to 127.0.0.1 or using a reverse proxy with authentication
Suggest firewall rules: ufw allow from 127.0.0.1 to any port 19000
For cloud servers: check security group rules

2. Container Isolation / 容器隔离

Recommend running OpenClaw in Docker with restricted capabilities:

docker run --cap-drop=ALL --cap-add=NET_BIND_SERVICE \
  --read-only --tmpfs /tmp \
  -u 1000:1000 \
  openclaw

Suggest resource limits: --memory=2g --cpus=1
Mount only necessary directories

3. Credential Management / 凭证管理

Scan for plaintext secrets in .env, .bashrc, environment variables
Recommend using a secret manager (Vault, doppler, etc.)
Check file permissions on sensitive files (should be 0600)
Suggest chmod 600 ~/.env ~/.ssh/* ~/.aws/credentials

4. Audit Logging / 审计日志

Verify ShellWard audit log is active at ~/.openclaw/shellward/audit.jsonl
Show recent security events
Recommend log rotation and backup strategy
Suggest sending critical events to external SIEM

5. Plugin Security / 插件安全

List all installed plugins and check for known risks
Disable auto-update for plugins
Only install from trusted sources
Scan plugin code for suspicious patterns

6. Patch Management / 补丁管理

Check current OpenClaw version
Report known vulnerabilities for current version
Recommend upgrade path
Check Node.js version (must be >= 22.12)

Available Commands

Remind the user about ShellWard's quick commands:

/security — Full security status overview
/audit [count] [filter] — View audit log
/harden — Scan for issues, /harden fix to auto-fix
/scan-plugins — Scan plugins for security risks
/check-updates — Check versions and vulnerabilities

Response Style

Be concise and actionable
Use the user's language (detect from their message)
Prioritize critical issues first
For each issue, provide the exact command to fix it
Ask for confirmation before executing destructive operations

Files

Just SKILL.md in skills/security-guide of jnMetaCode/shellward.

Open the folder on GitHubat commit 78444dd

Compare with similar skills

Security Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Security Guide compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Security Guide this skilljnMetaCode/shellward	140	—	~644	Automated safety check: Warn	Apache-2.0	9 days ago
Moai Ref LLM Securitymodu-ai/moai-adk	1.2k	—	~4.5k	Automated safety check: Pass	Apache-2.0	today
Reins Runtime Securitypegasi-ai/reins	392	—	~1.4k	Automated safety check: Warn	Apache-2.0	4 mo ago
PolygraphBankrBot/skills	1.2k	—	~3.4k	Automated safety check: Pass	None	2 days ago
Forensifyalexgreensh/repo-forensics	188	—	~2.5k	Automated safety check: Notes	Custom licence	11 days ago
AI SAFE2 Secure Build CopilotCyberStrategyInstitute/ai-safe2-framework	146	—	~2.7k	Automated safety check: Pass	Custom licence	today

Similar skills

Moai Ref LLM Security
modu-ai/moai-adk
AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and…
1.2k GitHub stars~4.5k tokensUpdated today
SecurityAuto-check passed
Reins Runtime Security
pegasi-ai/reins
Installs hooks that check each agent action against security policies before it runs, blocking destructive commands and logging every decision.
392 GitHub stars~1.4k tokensUpdated 4 mo ago
SecurityAuto-check: warnings
Polygraph
BankrBot/skills
Behavioral trust grades (A–F) for MCP servers. An agent skill from BankrBot/skills.
1.2k GitHub stars~3.4k tokensUpdated 2 days ago
Agent WorkflowsAuto-check passed
Forensify
alexgreensh/repo-forensics
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
188 GitHub stars~2.5k tokensUpdated 11 days ago
SecurityAuto-check: notes
AI SAFE2 Secure Build Copilot
CyberStrategyInstitute/ai-safe2-framework
Applies the AI SAFE2 v3.1 governance framework to designing, building, auditing and testing AI agents, RAG pipelines, MCP and tool integrations and AI infrastructure.
146 GitHub stars~2.7k tokensUpdated today
SecurityAuto-check passed
Plugin Scanner
iflytek/skillhub
Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them.
5.2k GitHub starsUsed in 2 repos~1.1k tokens
SecurityAuto-check: notes

More from jnMetaCode/shellward

China AI Compliance Audit
jnMetaCode/shellward
按中国法规（网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识）审计一个 AI 项目的代码仓库，产出每条都带文件:行取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's…
140 GitHub stars~1.1k tokensUpdated 9 days ago
Auto-check passed

Works with

Questions about Security Guide

What does Security Guide do?

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation. Security Guide is an agent skill from jnMetaCode/shellward.

When should I use Security Guide?

Security Guide fits situations like: tasks that involve Prompt injection and agent security; tasks that involve Deployment; tasks that involve LLM guardrails.

How do I install Security Guide in Claude Code?

Run `npx skills add jnMetaCode/shellward --skill security-guide -a claude-code`. Or copy the skill folder (skills/security-guide in jnMetaCode/shellward) into .claude/skills/security-guide in your project. Claude Code loads it when a task matches its description.

How do I install Security Guide in Codex?

Run `npx skills add jnMetaCode/shellward --skill security-guide -a codex`. Or copy the skill folder (skills/security-guide in jnMetaCode/shellward) into .agents/skills/security-guide in your project. Codex loads it when a task matches its description.

Can I use Security Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jnMetaCode/shellward --skill security-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-guide, .gemini/skills/security-guide, .github/skills/security-guide and .opencode/skills/security-guide in your project.

What does Security Guide need to run?

Going by SKILL.md and its folder, Security Guide needs the command-line tools its instructions call (docker). Our summary lists: Node.js; Docker.

Does Security Guide access the network?

SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Security Guide safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Security Guide use?

Security Guide is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Security Guide use?

About 644 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Security Guide?

Skills that share tags, products or a category with Security Guide: Moai Ref LLM Security (modu-ai/moai-adk, 1.2k stars), Reins Runtime Security (pegasi-ai/reins, 392 stars), Polygraph (BankrBot/skills, 1.2k stars) and Forensify (alexgreensh/repo-forensics, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Security Guide?

jnMetaCode (a GitHub user) maintains it in jnMetaCode/shellward, which has 140 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 28, 2026.

Source: jnMetaCode/shellward on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Security Guide

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ShellWard Security Deployment Guide / 安全部署指南

Security Checklist

1. Network Control / 网络控制

2. Container Isolation / 容器隔离

3. Credential Management / 凭证管理

4. Audit Logging / 审计日志

5. Plugin Security / 插件安全

6. Patch Management / 补丁管理

Available Commands

Response Style

Files

Compare with similar skills

Similar skills

Moai Ref LLM Security

Reins Runtime Security

Polygraph

Forensify

AI SAFE2 Secure Build Copilot

Plugin Scanner

More from jnMetaCode/shellward

China AI Compliance Audit

Related

Questions about Security Guide