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…
Agent skill
AI SAFE2 Secure Build Copilot
by CyberStrategyInstitute in 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.
Install AI SAFE2 Secure Build Copilot
$ npx skills add CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilot --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/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .claude/skills/ai-safe2-secure-build-copilot && 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 "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .claude/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilotType 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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .agents/skills/ai-safe2-secure-build-copilot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .agents/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .cursor/skills/ai-safe2-secure-build-copilot && 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 "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .cursor/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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/CyberStrategyInstitute/ai-safe2-framework.git --path skills/ai-safe2-secure-build-copilot--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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .gemini/skills/ai-safe2-secure-build-copilot && 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 "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .gemini/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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 CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilotInstalls 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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .github/skills/ai-safe2-secure-build-copilot && 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 "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .github/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CyberStrategyInstitute/ai-safe2-framework ai-safe2-secure-build-copilot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberStrategyInstitute/ai-safe2-framework.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-safe2-secure-build-copilot .opencode/skills/ai-safe2-secure-build-copilot && 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 "ai-safe2-secure-build-copilot" agent skill from https://github.com/CyberStrategyInstitute/ai-safe2-framework/tree/main/skills/ai-safe2-secure-build-copilot into .opencode/skills/ai-safe2-secure-build-copilot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-safe2-secure-build-copilot", 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
ai-safe2-secure-build-copilot- GitHub stars
- 147
- Token cost
- ~2.7k tokens
- SKILL.md length
- 1,140 words
- Files
- 2
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
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.
- Works in 7 steps: If governance is not enforced at… → Bind governance to verified principals,… → Treat NEXUS as CSI's reference… → …
- Designing the security architecture for a multi-agent system
- SKILL.md covers Governing Principles, When to Activate, Framework Architecture and v3.1 Enforcement Planes, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill has the agent reason with the AI SAFE2 Framework v3.1, which has 161 core controls across five operational pillars plus a cross-pillar governance layer, CP.1 through CP.10. Where a platform profile applies, it is added on top; for MCP that means the CP.5.MCP profile, MCP-1 through MCP-19. It activates for agents and swarms, RAG and persistent memory, tool-calling and A2A or MCP integrations, agent identity and delegation, runtime guardrails and human-in-the-loop controls, and for AI security reviews, red teaming and compliance work.
Governing principles shape the answers: governance must be enforced at runtime, framework controls stay separate from profile controls so the MCP profile does not change the total of 161, historical version facts are preserved, model prose is not evidence that a protected state change happened, and the system fails closed when an enforcement decision cannot be made safely. The agent classifies autonomy with ACT tiers, applies HEAR and replication governance where needed, treats NEXUS as a reference implementation and asks for reconstructable evidence behind material claims. The folder also carries ChatGPT and Gemini instructions, an MCP server setup and an evals file.
When your agent uses it
- Designing the security architecture for a multi-agent system
- Reviewing an MCP or tool-calling integration against framework controls
- Classifying an agent's autonomy tier and the governance it needs
- Preparing evidence for an AI governance or compliance review
Example prompts
- “Review our MCP server design against the CP.5.MCP controls and list the gaps.”
- “Classify this research agent's autonomy with ACT tiers and tell me which controls apply.”
- “Which AI SAFE2 pillars cover our RAG pipeline's memory writes and untrusted input?”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- If governance is not enforced at runtime, it is not governance.
- Bind governance to verified principals, authority, policy, provenance, and evidence, not to protocol-owned session constructs.
- Treat NEXUS as CSI's reference implementation, not as a mandatory dependency for AI SAFE² conformance.
- Separate framework controls from profile controls. AI SAFE² v3.1 remains 161 core controls; MCP profile controls do not make the total 180.
- Preserve historical version facts. A control introduced in v3.0 remains "introduced in v3.0" even when the current framework is v3.1.
- Do not treat model or agent prose as evidence that a protected state change occurred or was prevented.
- Fail closed when a required enforcement decision cannot be made safely.
What it can do on your machine
Read from SKILL.md and the folder at commit 065241a. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
AI SAFE2 Secure Build Copilot loads about 2.7k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 1,140 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.
Safety
Auto-check passed
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); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,140 words (~2,708 tokens).
“You apply the AI SAFE² Framework v3.1: 161 core controls across five operational pillars plus the core CP.1 through CP.10 Cross-Pillar Governance layer.”
- name
- ai-safe2-secure-build-copilot
- version
- 3.1.0
- framework_version
- v3.1
- framework_core_controls
- 161
- validation_source
- skills/mcp/data/ai-safe2-controls-v3.0.json
- profile_source
- skills/mcp/data/mcp-profile-v3.1.json
- mcp_server
- skills/mcp/
- tags
- security, GRC, AI-agents, AppSec, compliance, agentic-ai, non-human-identity, RAG-security, prompt-injection, supply-chain, swarm-governance, HEAR-doctrine…
Files
SKILL.md and 1 other file in skills/ai-safe2-secure-build-copilot of CyberStrategyInstitute/ai-safe2-framework.
- SKILL.md
- SKILL-CARD.md
Open the folder on GitHubat commit 065241a
Compare with similar skills
AI SAFE2 Secure Build Copilot 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 |
|---|---|---|---|---|---|---|
| AI SAFE2 Secure Build Copilot this skillCyberStrategyInstitute/ai-safe2-framework | 147 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| China AI Compliance AuditjnMetaCode/shellward | 140 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Slowmist Agent Securityslowmist/slowmist-agent-security | 508 | — | ~1.4k | Automated safety check: Pass | MIT | |
| MCP Server Security Auditawarexone/Agentic-Bug-Hunter | 5.3k | — | ~1.9k | Automated safety check: Warn | MIT | |
| Security ReviewChatbotXIO/ChatbotX | 885 | — | ~1.8k | Automated safety check: Notes | Custom licence | |
| Skill Scannersundial-org/awesome-openclaw-skills | 663 | 1 repos | ~364 | Automated safety check: Pass | None |
Similar skills
Slowmist Agent Security
slowmist/slowmist-agent-security
Comprehensive security review framework for AI agents. An agent skill from slowmist/slowmist-agent-security.
MCP Server Security Audit
awarexone/Agentic-Bug-Hunter
Audits MCP servers and their client configs for tool poisoning, prompt injection, over-privileged tools, injection bugs, secret leaks and missing approval gates.
Security Review
ChatbotXIO/ChatbotX
Use before committing changes to auth, workspace scoping, channel webhooks, AI tools/MCP, permission settings, or anything handling untrusted channel content in ChatbotX.
Skill Scanner
sundial-org/awesome-openclaw-skills
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them.
Sail
pillar-labs/sail-skill
Apply the SAIL (Secure AI Lifecycle) V2 framework by Pillar Security to secure AI applications and agents.
More from CyberStrategyInstitute/ai-safe2-framework
AI SAFE2 Secure Build Copilot
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.
AI SAFE2 Development Method
CyberStrategyInstitute/ai-safe2-framework
Plans and runs material repository changes with the AI SAFE2 method: classify delivery shape and risk, isolate the work, collect test evidence and finish with a completion receipt.
Related
Categories
Questions about AI SAFE2 Secure Build Copilot
What does AI SAFE2 Secure Build Copilot do?
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. 10.MCP profile, MCP-1 through MCP-19.
When should I use AI SAFE2 Secure Build Copilot?
AI SAFE2 Secure Build Copilot fits situations like: designing the security architecture for a multi-agent system; reviewing an MCP or tool-calling integration against framework controls; classifying an agent's autonomy tier and the governance it needs; preparing evidence for an AI governance or compliance review.
How do I install AI SAFE2 Secure Build Copilot in Claude Code?
Run `npx skills add CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a claude-code`. Or copy the skill folder (skills/ai-safe2-secure-build-copilot in CyberStrategyInstitute/ai-safe2-framework) into .claude/skills/ai-safe2-secure-build-copilot in your project. Claude Code loads it when a task matches its description.
How do I install AI SAFE2 Secure Build Copilot in Codex?
Run `npx skills add CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a codex`. Or copy the skill folder (skills/ai-safe2-secure-build-copilot in CyberStrategyInstitute/ai-safe2-framework) into .agents/skills/ai-safe2-secure-build-copilot in your project. Codex loads it when a task matches its description.
Can I use AI SAFE2 Secure Build Copilot 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 CyberStrategyInstitute/ai-safe2-framework --skill ai-safe2-secure-build-copilot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-safe2-secure-build-copilot, .gemini/skills/ai-safe2-secure-build-copilot, .github/skills/ai-safe2-secure-build-copilot and .opencode/skills/ai-safe2-secure-build-copilot in your project.
What does AI SAFE2 Secure Build Copilot need to run?
SKILL.md names no scripts, command-line tools or credentials: AI SAFE2 Secure Build Copilot is instructions for the agent only.
Does AI SAFE2 Secure Build Copilot access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is AI SAFE2 Secure Build Copilot safe to install?
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. Review the folder before installing.
What licence does AI SAFE2 Secure Build Copilot use?
AI SAFE2 Secure Build Copilot has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does AI SAFE2 Secure Build Copilot use?
About 2.7k tokens (SKILL.md is roughly 11k 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 AI SAFE2 Secure Build Copilot?
Skills that share tags, products or a category with AI SAFE2 Secure Build Copilot: China AI Compliance Audit (jnMetaCode/shellward, 140 stars), Slowmist Agent Security (slowmist/slowmist-agent-security, 508 stars), MCP Server Security Audit (awarexone/Agentic-Bug-Hunter, 5.3k stars) and Security Review (ChatbotXIO/ChatbotX, 885 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI SAFE2 Secure Build Copilot?
CyberStrategyInstitute (a GitHub organization) maintains it in CyberStrategyInstitute/ai-safe2-framework, which has 147 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: CyberStrategyInstitute/ai-safe2-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.