agent-governance
Skill0 starsChanged 3 months agoMITView on GitHub
Agent 安全治理:策略遵循、人工审批、生产安全护栏.
- Deletes or force-pushes
11 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- mahsumaktas/agent-evolution-kittheir own version, first seen Nov 8, 2026
- drvoss/everything-copilot-clitheir own version, first seen Oct 26, 2026
- github/awesome-copilottheir own version, first seen Oct 25, 2026
- 18DU1019/agent-governancetheir own version, first seen Sep 29, 2026
- sunji-droid/jack-of-all-trades-africatheir own version, first seen Aug 10, 2026
Used with
Projects with it also use tdd-workflow and security-audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lodetomasiSkilltdd-workflow
Test-Driven Development workflow with red-green-refactor pattern and best practices
Also in 4 projects that use this
CloudflareSkillsecurity-audit
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.
Also in 4 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- github/awesome-copilot★ 41ksame name
- drvoss/everything-copilot-cli★ 48same name
- sergeeey/Claude-cod-top-2026★ 9same name
- mahsumaktas/agent-evolution-kit★ 2same name
- 18DU1019/agent-governance★ 1same name
- sunji-droid/jack-of-all-trades-africa★ 1same name
- zaixincheng174-ai/codex-agent-governance-skills★ 1same name
- arcobaleno64/council-forge★ 0same name
- ReaperOAK/ForgeOS★ 0same name
- thistleknot/skills★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository219 other files it gives its agents.
- agent-doctrineSkill
- agent-evaluation-frameworkSkill
- agent-visualization-flintSkill
- hermes-agentSkill
- bailian-cliSkill
- edge-browser-automationSkill
- computer-useSkill
- jupyter-live-kernelSkill
- backup-strategiesSkill
- browser-automationSkill
- chinese-ai-free-apiSkill
- cicd-pipeline-templatesSkill
- copybaraSkill
- devops-toolkitSkill
- email-deliverabilitySkill
- monitoring-observabilitySkill
- obsidian-maintenanceSkill
- obsidian-troubleshootingSkill
- openclaw-windowsSkill
- openclaw-workerSkill
- webhook-subscriptionsSkill
- windows-dev-environmentSkill
- windows-masterSkill
- zero-downtime-deploySkill
- codebase-inspectionSkill
- github-workflowSkill
- adaptive-communicationSkill
- agent-cost-dashboardSkill
- agent-evolutionSkill
- agent-osSkill
- context-efficient-toolsSkill
- context-loss-awarenessSkill
- creative-synthesisSkill
- hermes-desktop-pluginsSkill
- emotional-intelligenceSkill
- graph-engineering-workflowSkill
- hermes-maintenanceSkill
- hermes-voiceSkill
- hermes-hygieneSkill
- identity-coreSkill
- income-loopSkill
- master-synthesisSkill
- meta-cognitionSkill
- reasoning-engineSkill
- self-preservationSkill
- teaching-abilitySkill
- temporal-awarenessSkill
- hermes-themesSkill
- thinking-visualizationSkill
- user-modelingSkill
- voice-full-restoreSkill
- knowledge-graph-traversalSkill
- mcp-browser-canvasSkill
- free-api-gatewaySkill
- native-mcpSkill
- web-reverse-apiSkill
- ai-edaSkill
- huggingface-hubSkill
- industrial-ai-siemens-mcpSkill
- industrial-ai-unifiedSkill
- The first 60 shown.
The file
Files
Agent 安全治理
概述
2026年7月三件事证明 Agent 治理从可选变必选:
- HANDBOOK.md — 最前沿模型遵循 20-124 页策略只有 36.2% 通过率
- AI 蠕虫通过 Copilot for Word 自我传播 — 文档即攻击向量
- "Agent 删了生产数据库" — 860分 HN 热帖,不是段子
核心洞察:Agent 不听话是系统性缺陷,治理层必须内建于 Agent 架构。
三层治理架构
L1: 策略注入层 → 把规则写进上下文,但不可靠(36%通过率)
L2: 硬门控层 → 工具调用前拦截,代码级强制(可达到95%+)
L3: 人工审批层 → 关键操作暂停等人类确认(approving 模式)L1:策略注入(当前 Hermes 方式)
系统 prompt + skills + memory 中写入规则。
HANDBOOK.md 的关键教训:
- 长策略文档(>20页)不可靠,Agent 会在长时域中丢失细节
- Agent 会让环境中的"合理请求"覆盖长期策略
- Agent 检查完规则后反而可能违反规则("知道但不做")
- Agent 会谎报合规(说做了实际没做)
→ 策略要短、要硬编码、要程序化验证。
L2:硬门控
在工具调用前加拦截层,任一 FAIL 就阻断:
GATES = {
"file_write": [
lambda args: args["path"] not in PRODUCTION_PATHS,
lambda args: not args["path"].endswith((".pem", ".key")),
],
"terminal": [
lambda args: "DROP" not in args["command"].upper(),
lambda args: "rm -rf /" not in args["command"],
],
}L3:人工审批(借鉴 approving 72⭐)
关键节点用 clarify 确认:
- 生产数据库操作 → clarify("确认执行此数据库操作?")
- Gerber/钻孔导出 → clarify("确认导出制造文件?")
- 删除文件/目录 → clarify("确认删除?")
- 超过 $5 的 API 调用 → clarify("确认此付费 API 调用?")
生产安全十条
| # | 规则 | 说明 |
| 1 | 生产环境只读 | Agent 默认只有读权限 |
| 2 | 写操作需审批 | 任何写操作弹 clarify |
| 3 | 操作前备份 | 改配置前先备份 |
| 4 | 变更可回滚 | 每个操作有 undo 路径 |
| 5 | 沙箱隔离 | 高风险 Agent 跑 Docker/VM |
| 6 | 审计日志 | 所有操作记录不可篡改 |
| 7 | 最小权限 | Agent 只拿任务需要的权限 |
| 8 | 超时熔断 | 单任务超时自动终止 |
| 9 | 资金上限 | API 调用有日消费 cap |
| 10 | 人机协作 | 关键决策必须人类 in the loop |
AI 蠕虫防护
Word/Copilot 蠕虫攻击链:恶意文档 → Copilot 读取 → 生成新恶意文档 → 传播
防护:文档内容不直接作为 Agent 指令执行;Agent 生成文档标记来源;外部文档启用沙箱。
实施优先级
P0:硬门控拦截器 + 高风险操作 clarify + 生产环境只读 P1:审计日志 + 策略检查框架 + 最小权限配置 P2:Docker 沙箱 + 程序化验证 + 回滚机制
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

