VulnClaw is an AI-driven command-line penetration-testing agent that turns natural-language instructions into an automated workflow for reconnaissance, vulnerability discovery, exploitation, and report generation. It is intended for authorized penetration tests, CTF competitions, security teaching, and red-team exercises, using LLMs and MCP tools. The catalogue contains its specialized skills for security-testing tasks.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Netw0rkNoob/VulnClaw --skill intranet-pentest-advancedgit clone --depth 1 https://github.com/Netw0rkNoob/VulnClawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/netw0rknoob/vulnclaw/intranet-pentest-advanced)<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/intranet-pentest-advanced"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/intranet-pentest-advanced/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/intranet-pentest-advanced"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/intranet-pentest-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 10 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high YARA Match · line 10 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00964 |
| Opus 5 | $0.00025 | $0.00482 |
| Sonnet 5 | $0.00010 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
intranet-pentest-advanced scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- intranet-pentest-advanced — 100% identical, 0 lines differ
- intranet-pentest-advanced — 100% identical, 0 lines differ
What it actually says
内网渗透高级 Skill
当任务从互联网评估转入主机、域或内网操作时使用本 Skill。需要已获得初始访问权限或立足点。
前置条件：如果尚未获得初始访问，先完成外网渗透获取立足点。
场景路由
| 目标类型 | 首选参考 |
|---|---|
| 横向移动（PsExec/WMI/WinRM/DCOM/SSH/RDP/PTH/PTT） | references/intranet-playbook-01-lateral-movement.md |
| 规避与反检测（AMSI绕过/ETW/注入/伪装/签名二进制滥用） | references/intranet-playbook-02-evasion-and-anti-detection.md |
| 凭据窃取（Mimikatz/Kerberoasting/DCSync/浏览器Vault） | references/intranet-playbook-03-credential-theft.md |
| 提权与持久化（Token/Service/Potato/Cron/Registry/WMI） | references/intranet-playbook-04-privilege-escalation.md + 05-persistence.md |
| 隧道与代理（FRP/Chisel/Ligolo/SOCKS/SSH/DNS/ICMP） | references/intranet-playbook-06-tunneling-and-proxy.md |
| 信息收集 | references/intranet-playbook-07-information-gathering.md |
| AD 攻击（BloodHound/AS-REP/Kerberoasting/Golden/Silver） | references/intranet-playbook-08-active-directory-attacks.md |
| ADCS 攻击（ESC1-8/Certipy/Certreq） | references/intranet-playbook-09-adcs-attacks.md |
| Exchange 攻击 | references/intranet-playbook-10-exchange-attacks.md |
| SharePoint 攻击 | references/intranet-playbook-11-sharepoint-attacks.md |
测试流程
1. 信息收集
- 内网拓扑、网段、主机发现
- 域信息、信任关系
- 服务识别与漏洞探测
2. 凭据获取
- Mimikatz 抓取内存凭据
- Kerberoating / AS-REP Roasting
- 浏览器/密码管理器凭据提取
- DCSync（需域管权限）
3. 横向移动
- Pass-the-Hash / Pass-the-Ticket
- PsExec / WMI / WinRM / DCOM
- SSH / RDP 横向
4. 权限提升
- Token 篡改 / 服务滥用
- Potato 家族
- 域提权（GPO/ACL滥用）
5. 持久化
- 计划任务 / WMI 事件订阅
- 注册表 / 启动项 / 服务
- 黄金票据 / 白银票据
6. 隧道与代理
- SOCKS 代理 / SSH 转发
- FRP / Chisel / Ligolo
- DNS / ICMP 隧道
7. AD/ADCS 专项
- BloodHound 路径分析
- ADCS 证书模板滥用
- Exchange/SharePoint 攻击链
参考文档
references/06-intranet-and-host-operations-integrated.md— 内网操作整合参考references/intranet-playbook-01~11-*.md— 各专项 Playbook（11 个）references/intranet-pentest-playbook-skill.md— Playbook 入口
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/06-intranet-and-host-operations-integrated.md 63 KB
- references/intranet-pentest-playbook-openai.yaml 306 B
- references/intranet-pentest-playbook-skill.md 2.7 KB
- references/intranet-playbook-01-lateral-movement.md 7.1 KB
- references/intranet-playbook-02-evasion-and-anti-detection.md 5.6 KB
- references/intranet-playbook-03-credential-theft.md 10 KB
- references/intranet-playbook-04-privilege-escalation.md 7.0 KB
- references/intranet-playbook-05-persistence.md 5.1 KB
- references/intranet-playbook-06-tunneling-and-proxy.md 5.1 KB
- references/intranet-playbook-07-information-gathering.md 7.1 KB
- references/intranet-playbook-08-active-directory-attacks.md 6.1 KB
- references/intranet-playbook-09-adcs-attacks.md 2.1 KB
- references/intranet-playbook-10-exchange-attacks.md 2.0 KB
- references/intranet-playbook-11-sharepoint-attacks.md 996 B
- references/intranet-playbook-index.md 740 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 77 lines · 50 tokens per session scan A 419ea0be669f
intranet-pentest-advanced is a skill published in the GitHub repository Netw0rkNoob/VulnClaw (3,299 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 964 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
clawmoat
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session…
minecraft-async
Manage a preinstalled local Minecraft Java client asynchronously for CTF and automation workflows. Use when an agent needs to launch Minecraft in offline mode with alternate usernames, inspect Minecraft logs, focus or type into the X11 game window, send chat or slash commands quickly, or join a multiplayer server by…
sagemath
Run SageMath through an explicit override, a detected environment named sage, or a PATH-resolved command. Use for CTF and cryptography work involving asymmetric cryptography, finite fields, elliptic curves, lattices, polynomial algebra, modular arithmetic, discrete logs, small-root attacks, or PRNG cryptanalysis.
opencrow-crypto-toolbox
Use the best available portable Python runtime and installed crypto tooling for CTF tasks that fit normal Python or CLI cracking rather than SageMath. Prefer a detected ctf environment. Use when an agent needs z3, fpylll, pycryptodome, hashcat, john, or quick FactorDB lookups.
opencrow-reversing-toolbox
Use the best available portable Python runtime and installed reverse-engineering tooling for binary analysis, symbolic execution, disassembly, emulation, and binary patching. Prefer a detected ctf environment. Use when an agent needs angr, claripy, capstone, unicorn, ghidra-headless, radare2, objdump, strace, ltrace…