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-playbookgit 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-playbook)<a href="https://agentmods.dev/skills/netw0rknoob/vulnclaw/web-security-playbook"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/web-security-playbook/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-playbook"><img src="https://agentmods.dev/badge/skills/netw0rknoob/vulnclaw/web-security-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.00880 |
| Opus 5.5 | $0.00026 | $0.00352 |
| Sonnet 5.5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
web-security-playbook 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Security Playbook
Use this skill for authorized security testing, defense validation, training, or documentation work.
When To Use
- The user needs a category-level web testing playbook rather than a single exploit recipe.
- The task involves choosing among multiple web attack families, payload styles, or bypass approaches.
- The user wants to turn the extracted wiki into narrower skills, checklists, notes, or reports.
When Not To Use
- A narrower existing skill already covers the request better.
- The task is primarily internal network, AD, Windows, Exchange, or SharePoint work.
- The user only needs a tool cheat sheet rather than attack-family guidance.
Workflow
- Start with
references/web-playbook-index.md, then narrow to 1-3 relevant category files. - If the request still spans multiple attack families, keep the answer grouped by category instead of by individual payload.
- If a specific payload entry is needed, use the packaged reference entries in
references/; any extracted source path still shown in entries should be treated as provenance only. - Return only the payload families, variants, prerequisites, bypass notes, OPSEC notes, and mitigations that match the authorized scope.
- When writing a new skill, checklist, or report, rewrite the selected material into the target format instead of copying whole reference files.
Category Map
- 点击劫持:
references/web-playbook-01-clickjacking.md - 供应链攻击:
references/web-playbook-02-supply-chain-attacks.md - 缓存与CDN安全:
references/web-playbook-03-cache-and-cdn-security.md - 开放重定向:
references/web-playbook-04-open-redirect.md - 框架漏洞:
references/web-playbook-05-framework-vulnerabilities.md - 请求走私:
references/web-playbook-06-request-smuggling.md - 认证漏洞:
references/web-playbook-07-authentication-vulnerabilities.md - 文件漏洞:
references/web-playbook-08-file-vulnerabilities.md - 业务逻辑漏洞:
references/web-playbook-09-business-logic-vulnerabilities.md - 原型链污染:
references/web-playbook-10-prototype-pollution.md - 云安全漏洞:
references/web-playbook-11-cloud-security-vulnerabilities.md - AI安全:
references/web-playbook-12-ai-security.md - API安全:
references/web-playbook-13-api-security.md - CSRF跨站请求伪造:
references/web-playbook-14-csrf-cross-site-request-forgery.md - JWT安全:
references/web-playbook-15-jwt-security.md - LFI/RFI文件包含:
references/web-playbook-16-lfi-rfi-file-inclusion.md - RCE远程代码执行:
references/web-playbook-17-rce-remote-code-execution.md - SQL/NoSQL注入:
references/web-playbook-18-sql-nosql-injection.md - SSRF服务端请求伪造:
references/web-playbook-19-ssrf-server-side-request-forgery.md - SSTI模板注入:
references/web-playbook-20-ssti-template-injection.md - WebSocket安全:
references/web-playbook-21-websocket-security.md - XSS跨站脚本:
references/web-playbook-22-xss-cross-site-scripting.md - XXE实体注入:
references/web-playbook-23-xxe-entity-injection.md
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.
- 1mo ago First seen · 63 lines · 64 tokens per session scan A e050ea7054e4
web-security-playbook is a skill published in the GitHub repository Netw0rkNoob/VulnClaw (3,785 stars, last pushed 12d ago), licensed MIT. It adds 64 tokens to every session and 880 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-13.
Other skills, from other repositories
netcat-async
Maintain bidirectional netcat-style TCP communications with persistent asynchronous input/output. Use when an agent must keep a connection open across multiple commands, send messages while receiving background output, inspect connection logs, or safely start/stop reusable sessions for protocol testing, CTF services…
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
api-auth
Authentication, authorization, and multi-tenancy patterns for @cyanheads/mcp-ts-core. Use when implementing auth scopes on tools/resources, configuring auth modes (none/jwt/oauth), working with JWT/OAuth env vars, or understanding how tenantId flows through ctx.state.