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 osint-recongit 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/osint-recon)<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/osint-recon"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/osint-recon/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/osint-recon"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/osint-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 46 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.
- high YARA Match · line 92 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.
- medium Data Exfiltration · line 129 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00042 | $0.02398 |
| Opus 5 | $0.00021 | $0.01199 |
| Sonnet 5 | $0.00008 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
osint-recon scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.get(f"https://crt.sh/?q=%.{domain}&output=json") Copies of this mod
1 near-identical copy found in the catalogue:
- osint-recon — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSINT 开源情报收集知识库
针对信息收集/侦察/社会工程场景的实战知识库，提供四维信息收集模型（服务器信息 → 网站信息 → 域名信息 → 人员信息），以及具体的工具使用方法和数据提取技巧。
与 recon Skill 的区别：
recon→ 技术层面侦察（端口扫描、DNS、目录枚举）— 基础版osint-recon→ 全维度侦察（服务器 + 网站 + 域名 + 人员/社会工程）— 深度版
核心原则
- 四维度全覆盖 — 服务器/网站/域名三个维度始终执行，人员维度按条件触发
- 从页面提取一切可提取的信息 — 不只看 HTTP 头，还要看 HTML 内容、JS 文件、注释
- 先被动后主动 — 先看响应头、DNS、WHOIS（被动），再做端口扫描/目录枚举（主动）
- 维度完成度自检 — 每轮检查哪些维度已完成 ✅，哪些未完成 ❌，全部完成后才允许 [DONE]
- 外部链接即线索 — 页面上的每个外部链接都可能是信息来源
- 结构化输出 — 所有发现汇总为 Markdown 报告
四维信息收集模型
维度一：服务器信息
| 检查项 | 工具/方法 | 说明 |
|---|---|---|
| 开放端口 & 服务版本 | MCP nmap / python_execute + socket |
全端口扫描或常见端口（21/22/80/443/3306/6379/8080/8443） |
| 真实 IP 探测 | DNS 历史记录 / 全局 Ping / 邮件头提取 | CDN 后的源站 IP — SecurityTrails/DNSHistory/全局Ping |
| 操作系统指纹 | TTL 推断 + nmap OS 检测 | Linux TTL≈64, Windows TTL≈128, Unix TTL≈255 |
| 中间件版本 | 响应头 Server + 错误页 + 特征文件 | Apache/Nginx/IIS/Tomcat 版本识别 |
| 数据库识别 | 端口探测 + 错误信息 + 特征行为 | MySQL(3306)/Redis(6379)/MongoDB(27017)/MSSQL(1433) |
维度二：网站信息
| 检查项 | 工具/方法 | 说明 |
|---|---|---|
| 网站架构 | 响应头 + 页面特征 + JS 库 | OS + 中间件 + 数据库 + 语言 + 框架 → 完整技术栈 |
| Web 指纹 | fetch + 响应特征匹配 |
CMS 类型、前端框架、JS 库、模板引擎 |
| WAF 检测 | wafw00f 逻辑 + 响应特征 | 拦截页面/特殊响应头/异常状态码 |
| 敏感目录 & 敏感文件 | python_execute + 常见路径字典 |
/admin /backup /config /api /robots.txt /sitemap.xml |
| 源码泄露 | 检查常见泄露路径 | .git/.svn/.DS_Store/.env/web.config/备份文件(.bak/.swp/.old) |
| 旁站查询 | 同 IP 反查域名 | 站长工具/微步在线/crt.sh 同 IP 查询 |
| C 段查询 | 同网段存活主机扫描 | nmap -sn 扫描 /24 网段 |
维度三：域名信息
| 检查项 | 工具/方法 | 说明 |
|---|---|---|
| WHOIS 注册信息 | python_execute + whois API/命令 |
注册人/注册商/NS 服务器/注册日期/到期日期 |
| ICP 备案信息 | 工信部备案查询 API | 仅中国大陆域名需查，境外域名无备案 |
| 子域名发现 | crt.sh + 爆破 + 搜索引擎 + DNS 区域传送 | 多方法交叉验证，确保覆盖全面 |
| DNS 记录全量 | python_execute + dnspython/socket |
A/CNAME/MX/TXT/NS/SPF/SOA 全量查询 |
| 证书透明度日志 | crt.sh / Censys / certspotter | 发现历史证书、子域名、关联域名 |
维度四：人员信息 ⚡ 条件触发
⚠️ 此维度仅在以下条件之一满足时才执行：
- 用户命令中明确提及"社会工程/社工/人员信息/作者追踪/人物画像"等
- 目标网站有明确作者信息（meta author、about 页面、联系方式）
What ships with it
7 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.
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 · 162 lines · 42 tokens per session scan A 4cc79b76ccd9
osint-recon is a skill published in the GitHub repository Netw0rkNoob/VulnClaw (3,299 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 2,398 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…