pentest-agent-os SKILL.md skillA
pentest-agent-os from aipentest/cyberstrikeai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aipentest/cyberstrikeai/pentest-agent-os@git:20260729.8882d70Pins git:20260729.8882d70 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aipentest/cyberstrikeai
- Path
skills/pentest-agent-os/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260729.8882d70, committed Jul 29, 2026
- First version recorded
- Jul 21, 2026
- Size
- 3,899 bytes
- Repository stars
- 7,963
- License
- Apache-2.0
渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法 (联网情报/Web/认证/服务端/源码/社工/后渗透/二进制/内网域/云/区块链/AI/无线/硬件)+0day+ 组合拳+代理自举。核心:全网搜不到洞时现场推导独属于目标的攻击链。本文件为套件索引。 Use when starting a full-chain pentest engagement or needing the skill map for this suite.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 渗透测试Agent操作系统 > **渗透不是执行脚本,是搜索路径。** > 不给自己预设固定路径/角色/已知利用链。给定起点与目标, > 路径未知 → 在状态空间里搜索:不断试不同路径、试错、反馈、逼近目标。 > **跳出固有攻击链** = 不问"它有没有已知CVE",而问"基于项目黑板上已掌握的事实,下一步最有效的动作是什么"。 > 状态落点见 `pentest-blackboard`（SQLite 项目事实，非磁盘 Intent/Hint 状态机）。 ## 套件映射（按作用分类） | 主题 | skill `name` | 作用 | |------|--------------|------| | 套件索引与核心心法 | `pentest-agent-os` | 套件索引与核心心法 | | 项目黑板 | `pentest-blackboard` | 项目 Fact 图 / 边记录 / 与漏洞分工 | | 验证铁律 | `pentest-verification` | 验证铁律（防幻觉） | | 能力原语 + 状态空间搜索 | `capability-primitive-search` | 能力原语凑链/状态空间搜索 | | 联网情报收集 | `component-vuln-intel` | 组件识别后联网搜洞 | | 侦察/攻击面测绘 | `attack-surface-recon` | 侦察与攻击面测绘 | | 初始访问/钓鱼/社工 | `initial-access-phishing` | 初始访问/钓鱼/社工 | | Web注入+认证+服务端+杂项+CDN | `web-attack-methods` | Web全栈攻击手法 | | 源码狩猎 | `source-code-hunting` | 源码/密钥/供应链狩猎 | | 后渗透/提权+凭据破解 | `post-exploitation` | 后渗透/提权/凭据/密码学 | | 内网域 | `active-directory-attack` | 内网域/AD攻击 | | APK/EXE/二进制 | `binary-mobile-reversing` | 移动端/二进制逆向 | | 云 | `cloud-attack-methods` | 云与对象存储攻击 | | 区块链/智能合约 | `blockchain-contract-attack` | 区块链/智能合约 | | AI/LLM应用 | `ai-llm-app-attack` | AI/LLM应用攻击 | | 无线/硬件 | `wireless-hardware-attack` | 无线与硬件攻击 | | 0day自主发现引擎 | `zero-day-discovery` | 0day/N-day自主发现 | …
Read the whole file at its exact version.
How to install
mdr add aipentest/cyberstrikeai/pentest-agent-os@sha256:215bdab3c8d932e9The line at the top of this page pins the label git:20260729.8882d70, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xxhngyhahcag3c2g)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 21, 2026 and Jul 29, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260729.8882d70 latest | 2026-07-29 | 8882d70 | 3,899 B | A | view · diff |
| git:20260721.2b63e3b | 2026-07-21 | 2b63e3b | 3,887 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3899 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aipentest/cyberstrikeai · 7,963 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xxhngyhahcag3c2g GET https://markdownregistry.com/api/v1/resolve?ref=aipentest/cyberstrikeai/pentest-agent-os GET https://markdownregistry.com/api/v1/blob/215bdab3c8d932e999bc5e0e56158e3dcd5751dc12cb4b843b66c26e8c37e7fa
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.