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 web-security-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/web-security-advanced)<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/web-security-advanced"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/web-security-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/web-security-advanced"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/web-security-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.01177 |
| Opus 5 | $0.00019 | $0.00589 |
| Sonnet 5 | $0.00008 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
web-security-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 10d 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
1 near-identical copy found in the catalogue:
- web-security-advanced — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web 高级安全测试 Skill
当目标是 Web 应用、API、网关或浏览器面向服务，且需要系统性的漏洞测试时使用本 Skill。
前置条件：如果请求仍由客户端控制且重放未稳定，先使用 client-reverse Skill。
CTF 场景路由
当目标为 CTF 题目（已知有 flag，需要绕过特定过滤）时，优先使用
ctf-webSkill 获取具体绕过值和 payload：
| CTF 场景 | 路由到 ctf-web | 参考文档 |
|---|---|---|
| PHP 弱比较/类型绕过 | ctf-web |
references/php-bypass-cheatsheet.md |
| 命令注入空格绕过 | ctf-web |
references/command-injection-bypass.md |
| eval 回显/无回显 | ctf-web |
references/eval-and-rce-techniques.md |
| PHP 代码审计 | ctf-web |
references/php-code-audit-checklist.md |
| SSTI 注入链 | ctf-web |
references/ssti-injection-chains.md |
| 反序列化利用链 | ctf-web |
references/deserialization-playbook.md |
| 文件上传 → RCE | 本 Skill | references/web-playbook-08-file-vulnerabilities.md |
本 Skill 侧重渗透测试方法论，CTF 实战绕过值和 payload 模板请参考 ctf-web。
场景路由
| 攻击面类型 | 首选参考 |
|---|---|
| 参数注入（SQLi/XSS/命令执行/SSTI/XXE） | references/web-injection.md |
| 协议安全（CORS/GraphQL/WebSocket/OAuth/请求走私） | references/web-modern-protocols.md |
| 认证与逻辑（IDOR/越权/支付/密码重置/鉴权绕过） | references/web-logic-auth.md |
| 文件与基础设施（上传/遍历/包含/部署/缓存/CDN/云） | references/web-file-infra.md |
| 部署安全 | references/web-deployment-security.md |
测试流程
1. 输入验证测试
- SQL 注入：布尔/时间/报错/Union/堆叠
- XSS：反射/存储/DOM/CSP 绕过
- 命令注入：分隔符绕过、编码绕过
- SSTI：模板引擎识别 + RCE 链
- XXE：实体注入、OOB 数据外带
- 反序列化：Java/PHP/Python 链
2. 认证与会话测试
- 默认凭据、暴力破解
- 会话管理缺陷（固定/劫持/不安全 Cookie）
- JWT 安全（算法篡改/密钥爆破/none算法）
- OAuth/OIDC 配置缺陷
- MFA 绕过
3. 逻辑漏洞测试
- 越权访问（水平/垂直）
- 业务逻辑绕过（支付/优惠券/投票）
- 竞态条件
- IDOR（不安全直接对象引用）
4. 协议安全测试
- CORS 配置错误
- GraphQL 内省/注入
- WebSocket 认证与注入
- HTTP 请求走私
- SSRF（内网探测/云元数据）
5. 文件与部署安全
- 文件上传绕过
- 路径穿越
- LFI/RFI
- CDN/缓存投毒
- 供应链攻击
- 云安全配置
参考文档
references/web-injection.md— 注入攻击详细参考references/web-modern-protocols.md— 现代协议安全references/web-logic-auth.md— 认证与逻辑漏洞references/web-file-infra.md— 文件与基础设施安全references/web-deployment-security.md— 部署安全references/web-ai-attack-map.md— Web 与 AI 攻击映射references/web-playbook-*.md— 各专项 Playbook（23 个）
What ships with it
33 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/web-ai-attack-map.md 562 B
- references/web-deployment-security.md 15 KB
- references/web-file-infra.md 18 KB
- references/web-injection.md 26 KB
- references/web-logic-auth.md 16 KB
- references/web-modern-protocols.md 10 KB
- references/web-playbook-01-clickjacking.md 1.4 KB
- references/web-playbook-02-supply-chain-attacks.md 2.2 KB
- references/web-playbook-03-cache-and-cdn-security.md 1.5 KB
- references/web-playbook-04-open-redirect.md 1.5 KB
- references/web-playbook-05-framework-vulnerabilities.md 8.1 KB
- references/web-playbook-06-request-smuggling.md 2.2 KB
- references/web-playbook-07-authentication-vulnerabilities.md 4.3 KB
- references/web-playbook-08-file-vulnerabilities.md 4.2 KB
- references/web-playbook-09-business-logic-vulnerabilities.md 3.5 KB
- references/web-playbook-10-prototype-pollution.md 2.3 KB
- references/web-playbook-11-cloud-security-vulnerabilities.md 2.9 KB
- references/web-playbook-12-ai-security.md 3.1 KB
- references/web-playbook-13-api-security.md 5.4 KB
- references/web-playbook-14-csrf-cross-site-request-forgery.md 3.7 KB
- references/web-playbook-15-jwt-security.md 2.8 KB
- references/web-playbook-16-lfi-rfi-file-inclusion.md 5.4 KB
- references/web-playbook-17-rce-remote-code-execution.md 5.3 KB
- references/web-playbook-18-sql-nosql-injection.md 7.8 KB
- references/web-playbook-19-ssrf-server-side-request-forgery.md 5.4 KB
- references/web-playbook-20-ssti-template-injection.md 4.7 KB
- references/web-playbook-21-websocket-security.md 2.4 KB
- references/web-playbook-22-xss-cross-site-scripting.md 5.2 KB
- references/web-playbook-23-xxe-entity-injection.md 3.6 KB
- references/web-playbook-24-php-regex-bypass.md 3.5 KB
- references/web-playbook-index.md 1.5 KB
- references/web-security-playbook-openai.yaml 296 B
- references/web-security-playbook-skill.md 3.6 KB
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.
- 10d ago First seen · 111 lines · 38 tokens per session scan A 77adf6a28394
web-security-advanced is a skill published in the GitHub repository Netw0rkNoob/VulnClaw (3,284 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,177 once invoked, about $0.0002 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…