REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
🐶 A curated list of Web Security materials and resources.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/qazbnm456-awesome-web-security)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 awesome-web-security | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | qazbnm456 | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 14,072 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年11月2日 | 2026年11月18日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | – | MIT | – | Apache-2.0 | MIT |
qazbnm456 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodex
依据开发者 README 和 repo 中的文件夹
GitHub account qazbnm456 (person), 12 years old
★ 14,072 stars · code last changed 2026年11月2日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 23b4ecc (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the skills/awesome-web-security folder again. The ZIP must have a awesome-web-security folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick awesome-web-security.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /awesome-web-security,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add qazbnm456/awesome-web-security -a claude-code -g -y摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/qazbnm456/awesome-web-security.git /tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc/skills/awesome-web-security' ~/.claude/skills/awesome-web-securityChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 awesome-web-security 文件夹放到 ~/.agents/skills/awesome-web-security
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/qazbnm456/awesome-web-security.git /tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc/skills/awesome-web-security' ~/.agents/skills/awesome-web-securityChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/qazbnm456/awesome-web-security.git /tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc/skills/awesome-web-security' ~/.agents/skills/awesome-web-security复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 awesome-web-security
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/qazbnm456/awesome-web-security.git /tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-qazbnm456-awesome-web-security-23b4ecc/skills/awesome-web-security' ~/.cursor/skills/awesome-web-security适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月16日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
5,295 个字符 · 在 GitHub 打开完整文件
---
name: awesome-web-security
description: "Looks up curated web security learning resources (XSS, SQLi, CSRF, SSRF, OAuth/JWT, deserialization, SAML, recon, evasion, defensive tooling, CTF). Filters by topic, difficulty, language, and resource type. Returns top references with archive fallbacks. Defensive and educational use only."
when_to_use: "XSS, SQL injection, CSRF, SSRF, XXE, OAuth, JWT, prototype pollution, deserialization, SAML, file upload, web cache poisoning, WAF evasion, CSP bypass, browser exploitation, subdomain enumeration, OSINT, web security, penetration testing references, bug bounty resources, CTF web challenges, payload list, security cheatsheet, awesome list, 资安, 渗透, 学习资源, 安全, 漏洞, セキュリティ, ペンテスト, 脆弱性"
metadata:
version: "1.0.0"
---
# /awesome-web-security
Curated lookup over [qazbnm456/awesome-web-security](https://github.com/qazbnm456/awesome-web-security).
Always fetches the latest index from `raw.githubusercontent.com` — no stale snapshot.
## When to use
A user asks for resources, references, learning paths, or tools related to web
security topics: XSS, SQLi, CSRF, SSRF, XXE, OAuth/JWT, prototype pollution,
deserialization, SAML, file upload, web cache poisoning, WAF / CSP evasion,
browser exploitation, recon (subdomain enumeration, OSINT), DNS rebinding,
CTF write-ups, bug bounty methodology, defensive tooling, payload lists,
cheatsheets, or related blogs.
## When NOT to use
- The user wants to attack a target they do not own and have not been
authorized to test. Decline and ask for scope: own system, CTF,
authorized pentest, academic research, or defensive analysis.
- The user is asking for malware authoring, mass scanning of unowned
infrastructure, or detection-evasion guidance for offensive purposes.
- The question has no security framing — it's general programming or
framework usage. Hand off to a non-security skill.
## How
1. Fetch the index with WebFetch:
`https://raw.githubusercontent.com/qazbnm456/awesome-web-security/master/data/index.json`
2. Parse the JSON. Schema:
```
{
"schema_version": "1",
"categories": [{"key": "xss", "title": "...", "h_level": 3, "parent": "intro", "anchor": "xss"}],
"entries": [{
"id": "xss-google-app-security",
"url": "...",
"title": "...",
"author": {"name": "...", "url": "..."},
"category": "xss",
"type": "article|tool|cheatsheet|video|book|community|payload-list",
"languages": ["en", "zh", "jp"],
"difficulty": "intro|intermediate|advanced",
"date_added": "YYYY-MM-DD",
"archive_url": "...|null",
"last_checked": "YYYY-MM-DD|null",
"status": "active|dead|archived-only|quarantined"
}]
}
```
3. Filter by:
- `category` matching the user's topic (a topic may map to several
categories — for "XSS" check `xss`, `tools-xss`, `tricks-xss`,
`practices-xss`, `evasions-csp` as relevant).
- `languages`: default to the user's language; fall back to `en`.
- `difficulty`: include all unless the user asked for "intro" or "deep".
- `type`: filter by what the user wants — articles, tools, cheatsheets,
payload lists, etc.
4. Rank by:
- "Latest" requests → `date_added` DESC.
- "Deep dive" requests → prefer `difficulty: advanced`, then by depth
signals (long titles, payload-list type, presence of author URL).
- "Tools" requests → `type: tool` only.
5. Return 5–7 entries; for each include title, URL, archive_url fallback if
`status != active`, and a one-line value statement explaining what this
entry teaches.
## Safety guardrails
- Refuse to assist with unauthorized targeting. Ask for scope.
- Frame all results defensively / educationally.
- For `payload-list` entries, append: "Test payloads only against systems
you own or have written authorization to test."
- Do not chain entries into an attack playbook against a named real target.
## Output format
For each result:
> **[Title](url)** — *author* • *difficulty* • *type*
> One line on what this teaches and why it matters.
> *(Archive fallback: archive_url)* — included only when `status != active`.
End with:
> Cited from [qazbnm456/awesome-web-security](https://github.com/qazbnm456/awesome-web-security). Full list and categories at the README.
## Failure handling
- JSON fetch fails (network, 404, parse error) → respond:
"The awesome-web-security index is temporarily unreachable. Try again
shortly, or visit https://github.com/qazbnm456/awesome-web-security
directly." Do NOT fabricate entries.
- No matches in the requested category → say so explicitly. Offer adjacent
categories from `categories[].parent` chain.
## Examples
User: "I'm learning XSS, give me intermediate-level resources in English."
→ Filter `category` matching `xss`, `tools-xss`, `tricks-xss`, `evasions-csp`;
`languages` contains `en`; `difficulty` in `intermediate` or `advanced`;
rank by `date_added` DESC; return top 5–7.
User: "我想找最新的 SSRF 文章。"
→ Filter `category` matching `ssrf`, `tricks-ssrf`, `tools-ssrf`;
`languages` contains `zh`; rank by `date_added` DESC; return in Chinese.
User: "What's a good XSS payload list?"
→ Filter `category: xss` AND `type: payload-list`; rank by depth signals.
Append the unauthorized-testing reminder.
提问、分享技巧或报告无法使用。按“有帮助”数量排序。