配套材料来自OpenClaw渗透测试实验——一项关于AI辅助红队在企业Active Directory环境中行动的探索。

目录

• AD-Recon-Authenticated-SKILL.md — 一套结构化的技能/方法论，用于Linux认证AD侦察，涵盖LDAP枚举、BloodHound摄取、Kerberoasting、委派分析、SMB枚举和攻击路径识别。
• matrix-claw-persona.txt — OpenClaw 红队代理的系统角色和操作约束，定义其指挥链、报告要求、权限边界和安全控制。
• legacy-ad-attack-paths-REDACTED.md — 交战期间生成的攻击路径分析输出的已删减示例，展示了该方法论所显示的发现类型。已净化后公开发布。
• OpenClaw-Architecture.md — NixOS 上 OpenClaw 平台的架构概述，涵盖基于片状的可重现性、声明式主机部署、技能与包管理，以及限制代理在参与主机上行为的保护措施。

背景

pentesting-skills

Accompanying materials from the OpenClaw pentesting experiment — an exploration of AI-assisted red team operations against enterprise Active Directory environments.

Contents

• AD-Recon-Authenticated-SKILL.md — A structured skill/methodology for authenticated AD reconnaissance from Linux, covering LDAP enumeration, BloodHound ingestion, Kerberoasting, delegation analysis, SMB enumeration, and attack path identification.
• matrix-claw-persona.txt — The system persona and operating constraints for the OpenClaw red team agent, defining its chain of command, reporting requirements, permission boundaries, and safety controls.
• legacy-ad-attack-paths-REDACTED.md — A redacted example of attack path analysis output produced during an engagement, demonstrating the type of findings the methodology surfaces. Sanitised for public release.
• OpenClaw-Architecture.md — Architecture overview of the OpenClaw platform on NixOS, covering flake-based reproducibility, declarative host deployment, skill and package management, and the guardrails that constrain agent behaviour on the engagement host.

Context

These materials were developed as part of a research project investigating how AI agents can be applied to penetration testing workflows. The skill file and persona define how the agent operates; the attack paths document is a representative (redacted) output.

Disclaimer

These materials are provided for educational and research purposes only. Use only in authorised engagements with explicit written permission.