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…
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jnMetaCode/shellward china-ai-compliance-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/china-ai-compliance-audit .claude/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.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/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .claude/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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 install https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-auditType 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.
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jnMetaCode/shellward china-ai-compliance-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/china-ai-compliance-audit .agents/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .agents/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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.
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jnMetaCode/shellward china-ai-compliance-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/china-ai-compliance-audit .cursor/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .cursor/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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 https://github.com/jnMetaCode/shellward.git --path skills/china-ai-compliance-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jnMetaCode/shellward china-ai-compliance-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/china-ai-compliance-audit .gemini/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.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/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .gemini/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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.
$ gh skill install jnMetaCode/shellward china-ai-compliance-auditInstalls 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).
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/china-ai-compliance-audit .github/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.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/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .github/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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.
$ npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jnMetaCode/shellward china-ai-compliance-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/shellward.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/china-ai-compliance-audit .opencode/skills/china-ai-compliance-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "china-ai-compliance-audit" agent skill from https://github.com/jnMetaCode/shellward/tree/main/skills/china-ai-compliance-audit into .opencode/skills/china-ai-compliance-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "china-ai-compliance-audit", 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.
china-ai-compliance-audit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…
China AI Compliance Audit is an agent skill from 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 codebase against China's regulations (CSL, PIPL, MLPS 2.0, cross-border data transfer, AI content labeling) with file:line evidence, independent verification and a deterministic validator.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts (for example `VERIFY.md`, `controls.json` and `examples/compliance-findings.example.json`).
It sits in Security, covering Prompt injection and agent security, AI governance and LLM guardrails. It works with OpenAI, 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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 78444dd. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (TypeScript and JavaScript), which the agent can run.
Shell commands in SKILL.md call:
npxnodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
China AI Compliance Audit loads about 1.1k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 270 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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); the scripts in this folder are not scanned.
The full file from jnMetaCode/shellward at commit 78444dd, republished under its Apache-2.0 licence (© jnMetaCode). 270 words, ~1,099 tokens.
.claude/skills/china-ai-compliance-audit/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.你现在是合规审计员。目标不是写一篇看起来专业的报告，而是产出一份每一条都能被人打开文件核对的记录。
三条铁律，违反任何一条这次审计作废：
shellward scan，你不重新发明它。文件:行 + 原文引用，就没有发现。 凭印象写的结论一律不算。needs_human，把问题问具体。在被审计项目根目录运行（只读、不上传）：
npx -y shellward@latest scan . --json > .compliance/baseline.json先 mkdir -p .compliance。跑不了（无网络 / 无 Node）就跳过，在最终记录里不写 baseline，并在给用户的总结里说明基线缺失。
基线怎么用：
projectScan.findings，每一条都要在阶段 2 分诊，不许原样照抄，也不许无视。controls[].status。那里的 pass 只表示「扫描器没扫到字面量」，不是「该控制项满足」——不要因为它写 met。baseline 填 { "tool": "shellward", "score": <score>, "grade": "<grade>" }，数字照抄 baseline.json。不要审计 skill 自己所在的目录（.claude/、.agents/ 等）和 .compliance/。
读代码，写 .compliance/architecture.md，只回答五个问题，每个回答都带 文件:行：
第 3 个问题最重要。扫描器只能告诉你「有境外端点」，你要回答的是「个人信息有没有真的流过去」。
读同目录的 controls.json。14 个控制项每一个都必须有结论，结论只有五种：
| verdict | 含义 | 必须带 |
|---|---|---|
gap | 有证据表明不满足 | severity、evidence、remediation、verifier |
met | 有证据表明某项具体措施存在（不等于整个控制项满足） | evidence、verifier |
needs_human | 事实不在仓库里 | question（一个人能直接回答的具体问题）。不许带 severity |
not_applicable | 项目没有这类场景 | reason，能引用代码就引用 |
rejected | 候选经核实不成立 | reason（留档，方便别人复审） |
按每个控制项的 look_for 去找。scope: "org" 的项通常是 needs_human。
一个控制项可以有多条记录，每条只对一个可证伪的命题下结论。 look_for 三条里两条找到措施、一条仓库里看不到，就写两条 met 加一条 needs_human，不要合成一条含糊的「基本满足」。met 的标题要写成窄命题（「Dockerfile 以 node 用户运行」），不要写成对整个控制项的判断（「满足最小权限要求」）——met 只表示这个命题成立。
gap 还是 needs_human？看证据是「有」还是「没有」：
gap。needs_human，把「仓库里没看到」作为 evidence 附上。gap。其它字段：
severity 取 critical / high / medium / low。controls.json 里控制项的 severity 是参考上限：按实际影响定，可以更低；要更高须在 verifier.note 说明理由。source：来自基线发现的写 baseline，你自己找到的写 agent。evidence 对 gap / met 必填；对 needs_human / not_applicable / rejected 可选，有就写。rejected 不计入覆盖：一个控制项的候选全被推翻后，要补一条 needs_human 或别的结论。基线发现的分诊，四种去向：
| 情形 | 处理 |
|---|---|
测试夹具、示例文档、.env.example 里的假数据 | rejected，写明为什么是假的 |
| 真实风险 | 挂到对应控制项下判 gap，source: "baseline" |
依赖是真的，但实际指向境内端点（如 openai SDK 的 baseURL 指向 DeepSeek） | rejected 并引用 baseURL 所在行；若 baseURL 来自环境变量，再补一条 needs_human 问生产环境的实际取值 |
| 与另一条是同一件事（依赖声明 + 调用点） | 并入主记录，本条 rejected，reason 写「重复，已并入 F-xxx」 |
引用密钥和个人信息时只引到它之前。例如原文是 const KEY = "sk-abc…"，quote 写 const KEY = "sk-。合规报告自己不能泄漏数据，校验器会拦。
每一条 gap 和 met 都要被试图推翻一次。详细协议见 VERIFY.md。
verifier.mode 写 independent。verifier.mode 写 self-recheck（校验器会警告，报告里会如实标注）。被推翻的改成 rejected 并写 reason，不要删。
把全部记录写进 .compliance/compliance-findings.json（格式见 examples/compliance-findings.example.json），然后运行本 skill 目录下的校验器：
node <本skill目录>/scripts/validate-findings.mjs .compliance/compliance-findings.json --root . --report .compliance/COMPLIANCE-REPORT.md校验器会核对：每条引用的文件和行真的存在、quote 真的出现在那几行、报告里没有泄漏密钥或证件号、裁决纪律、14 项全覆盖。
没通过就修到通过为止。 报错说 quote 找不到，就回到原文重新取证——不要改 quote 去凑。报告由校验器从记录直接渲染，你不要手写或改写 COMPLIANCE-REPORT.md。
用五六句话说清：
然后停下。不要主动开始改代码，除非用户要求。
controls.json 为准，不要凭记忆补充条款号。© jnMetaCode, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files (scripts) in skills/china-ai-compliance-audit of jnMetaCode/shellward.
Open the folder on GitHubat commit 78444dd
China AI Compliance Audit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| China AI Compliance Audit this skilljnMetaCode/shellward | 140 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Red Teaming LLMs With Garakmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.9k | Automated safety check: Warn | Apache-2.0 | |
| AI SAFE2 Secure Build CopilotCyberStrategyInstitute/ai-safe2-framework | 147 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Sailpillar-labs/sail-skill | 113 | — | ~5.1k | Automated safety check: Pass | Custom licence | |
| AI SAFE2 Secure Build CopilotCyberStrategyInstitute/ai-safe2-framework | 147 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Moai Ref LLM Securitymodu-ai/moai-adk | 1.2k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 |
mukul975/Anthropic-Cybersecurity-Skills
Runs NVIDIA garak probe suites (jailbreak, prompt injection, data leakage, toxicity, and more) against an LLM endpoint - Hugging Face models, OpenAI-compatible APIs, or Bedrock - then interprets the…
CyberStrategyInstitute/ai-safe2-framework
Applies the AI SAFE2 framework to security reviews, code reviews and compliance mapping for AI agents, RAG pipelines and MCP servers.
pillar-labs/sail-skill
Apply the SAIL (Secure AI Lifecycle) V2 framework by Pillar Security to secure AI applications and agents.
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.
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…
wuyoscar/AISafetyHot-Hub
Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.
jnMetaCode/shellward
OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation
Works with
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…. China AI Compliance Audit is an agent skill from jnMetaCode/shellward.0, cross-border data transfer, AI content labeling) with file:line evidence, independent verification and a deterministic validator.
China AI Compliance Audit fits situations like: tasks that involve Prompt injection and agent security; tasks that involve AI governance; tasks that involve LLM guardrails.
Run `npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a claude-code`. Or copy the skill folder (skills/china-ai-compliance-audit in jnMetaCode/shellward) into .claude/skills/china-ai-compliance-audit in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a codex`. Or copy the skill folder (skills/china-ai-compliance-audit in jnMetaCode/shellward) into .agents/skills/china-ai-compliance-audit in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/china-ai-compliance-audit, .gemini/skills/china-ai-compliance-audit, .github/skills/china-ai-compliance-audit and .opencode/skills/china-ai-compliance-audit in your project.
Going by SKILL.md and its folder, China AI Compliance Audit needs TypeScript and JavaScript for the scripts in its folder and the command-line tools its instructions call (npx and node). Our summary lists: Node.js.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
China AI Compliance Audit is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with China AI Compliance Audit: Red Teaming LLMs With Garak (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), AI SAFE2 Secure Build Copilot (CyberStrategyInstitute/ai-safe2-framework, 147 stars), Sail (pillar-labs/sail-skill, 113 stars) and AI SAFE2 Secure Build Copilot (CyberStrategyInstitute/ai-safe2-framework, 147 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.
