Security Copilot — Security skill for Claude Code
AI 安全运营助手(Security Copilot):接入 817 个开源安全技能,用自然语言完成告警研判、技能推荐与 MITRE/NIST 映射报告生成.
How to install Security Copilot
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open kiki-lgtm-dot/security-copilot and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Security Copilot does
AI 安全运营助手(Security Copilot):接入 817 个开源安全技能,用自然语言完成告警研判、技能推荐与 MITRE/NIST 映射报告生成.
Alternatives in Security
- FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
- Defense In Depth — Implement multi-layered testing and security best practices 98.1k ★
- Google Workspace Alert Center — Manage security alerts 21.6k ★
README
🛡️ AI 安全运营助手(Security Copilot)
一个接入 817 个开源安全技能的 AI 助手,让安全团队用自然语言完成
「告警研判 → 技能推荐 → 排查步骤 → MITRE/NIST 映射报告」全流程
它能做什么
安全分析师把一条告警 / 日志片段 / 现象描述粘贴进去,这个助手会:
| # | 能力 | 说明 |
|---|---|---|
| 1 | 技能检索与推荐 | 从 817 个安全技能中秒级匹配 Top 5,并解释"为什么推荐"(命中哪些关键词) |
| 2 | 告警研判 | 生成一步步可执行的排查计划(每步含工具名 + 期望输出) |
| 3 | 合规报告生成 | 自动输出含 MITRE ATT&CK 与 NIST CSF 映射的 Markdown 报告,可直接用于审计 |
| 4 | 攻击性技能拦截 Gate | 红队 / 渗透 / C2 / 攻击执行类技能(共 136 个)自动拦截,只开放防御侧,合规可控 |
**示例**:输入「LSASS 进程被异常访问,疑似凭据窃取」→
推荐技能:detecting-credential-dumping-techniques(threat-detection)
detecting-t1003-credential-dumping-with-edr(threat-hunting)
detecting-mimikatz-execution-patterns(threat-hunting)
detecting-pass-the-hash-attacks(threat-hunting)
排查步骤:1. 确认告警来源与时间线 → 2. 按技能执行取证 → 3. 交叉验证形成结论
报告映射:MITRE ATT&CK T1003 · NIST CSF RS.AN-03
它基于什么做的
本项目是站在巨人肩膀上的产品化封装,核心安全知识来自开源项目:
**[Anthropic-Cybersecurity-Skills](https://github.com/mukul975/Anthropic-Cybersecurity-Skills)** by [@mukul975](https://github.com/mukul975) —— 817 个安全技能、29 个领域、6 大框架映射(MITRE ATT&CK / NIST CSF / D3FEND / ATLAS / AI RMF / F3),Apache 2.0 可商用。
我们做的产品化工作(不重复造轮子):
| 层 | 本项目做的事 |
|---|---|
| 技能层 | 直接复用 817 个 skill(skills-repo/,只读),零改造 |
| 检索层 | 基于 index.json + frontmatter 的关键词打分检索 + 中文安全术语词典 |
| 安全层 | 授权 Gate:防御/攻击分类,攻击性技能拦截留痕 |
| 编排层 | FastAPI + LLM(DeepSeek / 任意 OpenAI 兼容模型)生成研判与报告 |
技能与模型解耦:任何支持 OpenAI 兼容接口的 LLM(DeepSeek / GPT / 开源模型)都可接入。
快速开始
1. 环境要求
- Python 3.9+(已验证 3.9.6)
- Git
- DeepSeek API Key(可选,没有则用 mock 跑通链路)
Related Skills
Anthropic Cybersecurity Skills
734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work
Coverage Checklist
Instantiate the internal-network pentest coverage checklist for an engagement. Copies the master template (met
Cve MCP Server
Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS sco
Security Threat Intel
Security Threat Intelligence skill for AI code review agents — MITRE ATT&CK infostealer mapping, detection che
My Security Auditor
Comprehensive Claude skill for authorized security auditing — OWASP, MITRE ATT&CK, ISO 27001, SOC 2, PCI-DSS,
Securevector AI Threat Monitor
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt inj
Related Agents
Sec Researcher
Read-only security research for ClaudeSec — threats, CVEs, attack vectors, and compliance frameworks (NIST, IS
AI Agent Security
AI / Agent Security specialist (NIST SP 800-218A profile; SSDF PS.1 AI artifacts, PW.3 data integrity). Read-o
Engineering Threat Detection Engineer
Expert detection engineer specializing in SIEM rule development, MITRE ATT&CK coverage mapping, threat hunting