Anthropic-Cybersecurity-Skills
库mukul975/Anthropic-Cybersecurity-Skills
为AI代理提供的结构化网络安全技能库，映射5个框架。
项目简介
为AI代理提供的754个结构化网络安全技能库，涵盖26个安全领域，并映射到MITRE ATT&CK、NIST CSF等五个框架。使代理能够执行威胁狩猎、事件响应、渗透测试等专家级安全任务。
README 预览
\n \n\n\n\n\n# Anthropic Cybersecurity Skills\n\n### The largest open-source cybersecurity skills library for AI agents\n\n[](https://mahipal.engineer/survey?utm_source=github_badge&utm_medium=readme&utm_campaign=gars2026)\n[](LICENSE)\n[](#whats-inside--26-security-domains)\n[](#five-frameworks-one-skill-library)\n[](#whats-inside--26-security-domains)\n[](#compatible-platforms)\n[](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/stargazers)\n[](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/network/members)\n[](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/commits/main)\n[](https://agentskills.io)\n[](CONTRIBUTING.md)\n[](https://casky.ai/?utm_source=github&utm_medium=readme&utm_campaign=cohort_launch#waitlist)\n[](https://github.com/NousResearch/hermes-agent)\n\n\n**754 production-grade cybersecurity skills · 26 security domains · 5 framework mappings · 26+ AI platforms**\n\n[Get Started](#quick-start) · [What's Inside](#whats-inside--26-security-domains) · [Frameworks](#five-frameworks-one-skill-library) · [Platforms](#compatible-platforms) · [Contributing](#contributing)\n\n\n\n---\n\n> ⚠️ **Community Project** — This is an independent, community-created project. Not affiliated with Anthropic PBC. \n\n## Give any AI agent the security skills of a senior analyst\n\nA junior analyst knows which Volatility3 plugin to run on a suspicious memory dump, which Sigma rules catch Kerberoasting, and how to scope a cloud breach across three providers. **Your AI agent doesn't — unless you give it these skills.**\n\nThis repo contains **754 structured cybersecurity skills** spanning **26 security domains**, each following the [agentskills.io](https://agentskills.io) open standard. Every skill is mapped to **five industry frameworks** — MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, and NIST AI RMF — making this the only open-source skills library with unified cross-framework coverage. Clone it, point your agent at it, and your
常见问题 (2)
故障排除如何在提交pull request之前本地验证SKILL.md元数据？
故障排除
如何在提交pull request之前本地验证SKILL.md元数据？使用内置脚本 tools/validate-skill.py。对单个技能运行：python tools/validate-skill.py skills/my-new-skill/ 它会检查必需的 frontmatter 字段、kebab-case 名称、描述长度、标签格式、子域名允许列表、折叠标量处理等。批量验证请使用 python tools/validate-skill.py --all。该脚本以正确的退出码退出，适合用于 CI。
故障排除为什么我在下载仓库压缩包时，Windows Defender 检测到 Trojan:Script/Wataca.Cm!c？
故障排除
为什么我在下载仓库压缩包时，Windows Defender 检测到 Trojan:Script/Wataca.Cm!c？这是一个误报。该存储库包含用于网络安全的代码片段（例如，Invoke-Expression、Set-MpPreference 等 PowerShell 模式），这些模式与 Windows Defender 中的启发式签名匹配。该存储库是安全的。如需抑制警报，请将该文件夹添加到 Defender 的排除列表，或在解压时暂时禁用实时扫描。