agent-governance官方

github/awesome-copilot/skills/agent-governance

添加治理安全和信任控制到 AI 代理系统

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

把下面的话发给 Claude Code、Codex 或 Cursor。智能体会先检查内容，经你确认再安装。

请帮我安装这个 Agent Skill：https://github.com/github/awesome-copilot/tree/main/skills/agent-governance

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/agent-governance/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

安装到个人 Skill 目录（对所有项目生效）。只想在当前项目用，改为 .claude/skills/。

git clone --depth 1 --filter=blob:none --sparse https://github.com/github/awesome-copilot.git /tmp/agent-governance-src
cd /tmp/agent-governance-src && git sparse-checkout set "skills/agent-governance"
mkdir -p ~/.claude/skills && cp -r "skills/agent-governance" ~/.claude/skills/agent-governance

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。

SKILL.md

在 GitHub 查看

正在从 GitHub 读取……