Skip to content

Redteam Skill

Redteam / Pentest Skill Pack — semi-automated workflow + on-demand module selection + real-world attack chains | Kali + Claude Code 红队/渗透/技能包 - 半自动工作流 + 按需点选模块 + 实战利用链 | 基于…

Install

$git clone https://github.com/pale-knight/redteam-skill

Install command taken from the project's README or registry entry. Always review code before running it.

redteam-skill Based on Kali+Claude code Semi-automated Redteam Workflow · 红队半自动工作流

Why so serious?

🌐 English · 日本語

关于项目

辅助红队工作,操作者通过/module选择模块,AI将取得的成果记录在notes.md中供操作者研判并建议下一模块,并在自身无法做到需要操作者辅助,例如:监听/sudo/输密码/Permission denied等情况时停止并等待操作者完成

本项目面向红队工作 / 靶场 / HTB 等场景,提供半自动红队工作流。

做成半自动是因为真实红队中,合格的渗透人员必须根据现场情况做研判并选择下一步,而不是把整条链路交给 AI。AI 可能执行不该执行的动作或者漏掉重要的信息,并无法承担相应的责任和带来的后果。所以也没有限制目标授权的范围,这也应该交由渗透人员负责。

此项目集成了绝大部分技能模块、最近工作中的高成功率利用链,以及 2025–2026 较新的技术路径,并会持续更新。

为了缩短上下文,节约token。此项目将每一模块的重要发现和成果记录在notes.md中,当前模块结束时可由人工/clear清除上下文。在每一个模块开始时会自动读取notes.md中数据,以保证工作延续。并且将每一模块的详细操作流程放入references中,只在遇到时才会读取对应的references/<file>.md。

项目架构

基本架构

18 个模块,每个模块为SKILL.md(判断基本方向)和一个references/(详细操作流程)。

CLAUDE.md                  # 全局规则,放进项目目录使用
skills/
├── recon/                     # 通用信息收集
│   ├── SKILL.md
│   └── references/     (11)
├── service-attack/            # 服务漏洞利用
│   ├── SKILL.md
│   └── references/     (13)
├── web-recon/                 # Web攻击面测绘
│   ├── SKILL.md
│   └── references/     (5)
├── web-attack/                # Web漏洞利用
│   ├── SKILL.md
│   └── references/     (24)
├── ad-recon/                  # AD枚举
│   ├── SKILL.md
│   └── references/     (5)
├── ad-attack/                 # AD攻击利用
│   ├── SKILL.md
│   └── references/     (9)
├── cloud-recon/               # AWS/Azure/GCP/阿里云枚举
│   ├── SKILL.md
│   └── references/     (7)
├── cloud-attack/              # 云控制面利用
│   ├── SKILL.md
│   └── references/     (9)
├── k8s/                       # 容器与集群
│   ├── SKILL.md
│   └── references/     (6)
├── cicd/                      # CI/CD与供应链
│   ├── SKILL.md
│   └── references/     (12)
├── phishing/                  # 钓鱼和客户端攻击
│   ├── SKILL.md
│   └── references/     (8)
├── privesc-win/               # Windows提权
│   ├── SKILL.md
│   └── references/     (5)
├── privesc-linux/             # Linux提权
│   ├── SKILL.md
│   └── references/     (5)
├── creds/                     # 凭据攻击
│   ├── SKILL.md
│   └── references/     (7)
├── post/                      # 后渗透利用与C2
│   ├── SKILL.md
│   └── references/     (7)
├── shell/                     # shell稳定化
│   ├── SKILL.md
│   └── references/     (6)
├── tunnel/                    # 内网穿透
│   ├── SKILL.md
│   └── references/     (7)
├── edr-bypass/                # AV/EDR规避
│   ├── SKILL.md
│   └── references/     (12)
├── shared/                    # 跨模块共享
│   ├── modules.yaml           # 模块目录
│   ├── cve-enrichment.md      # 全Skill漏洞情报入口
│   ├── tools.md               # 工具注册表
│   └── wordlists.md           # 字典路径
└── bin/
    ├── modules.py             # tail / list / show / check,模块控制和收尾
    └── notes.py               # init / validate,操作记录文件notes.md

references/内共 158 份操作文档,按SKILL.md 判断选择加载,不计入常驻上下文。

模块介绍

Similar plugs

Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get…

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in…

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection…