Security

Security agent skills give AI agents disciplined security workflows: code review for vulnerabilities, secret handling, dependency audits, and hardening checklists. Every skill on SkillMD also passes its own safety review before listing, with capability flags shown on each page.

wgpsec Bundle

Mongodb Attack

MongoDB 未授权访问与 NoSQL 注入利用。当发现目标开放 27017 端口、MongoDB 服务无认证、Web 应用使用 MongoDB 后端存在 NoSQL 注入、或需要从 MongoDB 提取数据时使用。覆盖未授权访问、数据库枚举与导出、NoSQL 注入（$ne/$regex/$where/盲注）、JavaScript 执行（mapReduce/eval）、权限提升、GridFS 文件提取、配置文件凭据

Sep 17
wgpsec Bundle

GRAPHQL Methodology

GraphQL API 安全测试。当发现 /graphql 端点、POST JSON 查询、GraphQL Playground/Explorer 页面、响应中有 data/errors JSON 结构时使用。包含 Introspection 泄露、注入攻击、权限绕过、嵌套查询 DoS

Audited Sep 17
wgpsec Bundle

Lfi Rfi Methodology

本地文件包含(LFI)/远程文件包含(RFI)/任意文件读取的检测和利用。当目标有文件包含参数(page/file/include/lang)、PHP应用、日志文件可写时使用。包含file_exists()陷阱、PHP include()语法错误诊断、日志投毒正确payload、pearcmd.php利用、PHP filter chain RCE、session文件包含条件竞争

Sep 17
wgpsec Bundle

Race Condition Exploit

竞态条件漏洞利用方法论。当目标有余额/积分操作、优惠券兑换、限量库存、频率限制、多步骤工作流（注册/密码重置/MFA）时使用。核心技术：HTTP/2 单包攻击（Single-Packet Attack）、Turbo Intruder、Last-Byte Sync

Sep 17
wgpsec Skill

Captcha Bypass Methodology

图片验证码/点击式验证码（click captcha）绕过与识别方法论。当目标登录、注册、密码重置、短信发送等接口存在图片验证码、点击验证码、滑块验证码需要绕过或识别时使用。覆盖验证码类型识别、OCR/打码平台识别、点击坐标验证码模拟、验证码逻辑绕过（复用/回显/空值）、频率限制绕过与授权边界

Sep 17
wgpsec Skill

Password Reset Methodology

密码重置与用户注册/越权修改方法论。当目标存在忘记密码/密码重置、验证码回显、校验绕过、任意用户密码修改、越权注册（registersysuser、goedituser 等接口）、thinkphp 商城登录短信验证码等场景时使用。覆盖密码重置链路分析、验证码回显/爆破、短信验证码绕过、任意用户密码修改与越权注册、spring 类 .do 接口鉴权绕过（login_tologin.do 等）与授权边界

Sep 17
wgpsec Bundle

Java Serialization Audit

Java 源码序列化类漏洞审计。当在 Java 白盒审计中需要检测序列化/反序列化相关漏洞时触发。覆盖 3 类风险: Java 原生反序列化(ObjectInputStream/Gadget Chain/ysoserial)、 XXE(DocumentBuilderFactory/SAXParser/XMLInputFactory/TransformerFactory/SchemaFactory 五种解析器)、模板注入 SSTI(Velocity/FreeMarker/Thymeleaf 模板引擎代码执行)。 Java 反序列化是 Java 生态最具特色的高危漏洞类型，Gadget Chain 分析是核心难点。

Sep 17
wgpsec Bundle

HTTP Smuggling Advanced

HTTP 请求走私高级利用方法论。扩展 cache-poisoning-smuggling 的走私部分。当已确认存在 CL.TE/TE.CL/TE.TE/H2.CL 走私时使用。覆盖链式利用（窃取凭据、绕过 ACL、投毒 Web 缓存、XSS 其他用户）和 HTTP/2 降级走私

Sep 17
wgpsec Bundle

Business Logic Attack

Web 应用业务逻辑漏洞检测与利用。当目标有支付/交易/订单/优惠券/积分/余额/充值/转账/购物车等商业功能时使用。当发现用户注册/登录/短信验证码/邮箱验证/密码重置等账户功能时使用。当 API 请求中出现价格(price/amount)、数量(quantity/count)、订单号(order_id)、优惠码(coupon/promo)等业务参数时使用。业务逻辑漏洞不需要技术漏洞（SQLi/XSS），而是利用应用流程设计缺陷——负数金额、0元支付、订单状态篡改、验证码复用、并发竞争。SRC 众测和实战渗透中最高频的漏洞类型之一，每个有交易功能的应用都应检查

Sep 17
wgpsec Bundle

AI Infrastructure Attack

AI/ML 基础设施安全测试。当目标涉及 Jupyter Notebook/JupyterHub/JupyterLab、MLflow、Ray Dashboard、Kubeflow、Gradio/Streamlit 应用、vLLM/TGI/Ollama 推理服务、或任何机器学习平台时使用。当发现端口 8888(Jupyter)/5000(MLflow)/8265(Ray)/8080(Kubeflow)/7860(Gradio)/8501(Streamlit)/11434(Ollama) 时使用。AI 基础设施是云安全比赛和实战中的新兴高价值目标——很多 AI 平台默认无认证或弱认证，直接提供代码执行能力。发现任何 AI/ML 相关服务、模型训练/推理平台、notebook 环境时都应使用此 skill

Sep 17
wgpsec Bundle

File Upload Methodology

任意文件上传的检测、绕过和利用。当目标有上传功能(头像、附件、导入)、multipart表单、文件管理接口时使用。包含扩展名/Content-Type/Magic Bytes三层绕过、.htaccess覆盖、.user.ini+auto_prepend_file、图片马二次渲染绕过、ZIP解压利用、上传路径猜解方法

Sep 17
wgpsec Bundle

HTTP Host Header Attacks

HTTP Host Header 攻击方法论。当目标存在密码重置、缓存机制、反向代理、虚拟主机、重定向功能时使用。覆盖密码重置投毒(Host注入窃取reset token)、Web缓存投毒(Host控制缓存键)、通过Host路由SSRF、虚拟主机枚举与跨站读取、绕过技术(X-Forwarded-Host/双Host/绝对URI/端口注入/换行符注入)。任何涉及密码重置、Host头处理、缓存、虚拟主机配置的测试都应使用此 skill

Sep 17
wgpsec Bundle

Privilege Escalation Web

Web 应用层权限提升。当 Web 应用存在用户注册/登录、角色权限管理、API 参数传输用户身份信息时使用。覆盖 Mass Assignment（批量赋值）攻击、角色/权限字段注入、HTTP 方法/Header 绕过、Cookie/Session 篡改。注册后立即检查普通用户能否越权访问管理员功能——这是第一优先级

Sep 17
wgpsec Bundle

Cache Poisoning Smuggling

Web 缓存投毒和 HTTP 请求走私。当目标使用 CDN/反向代理/缓存层（Cloudflare/Varnish/Nginx）、或有前后端服务器架构差异时使用。通过操纵缓存键或利用 HTTP 解析差异来投毒缓存或绕过安全控制。高级 Web 攻击技术

Sep 17
wgpsec Bundle

Python Prototype Pollution

Python 原型链污染（属性注入/Class Pollution）检测与利用。当目标为 Python Web 应用（Flask/Sanic/Django/FastAPI）且存在递归合并(merge)、深度属性设置(pydash.set_)、JSON 配置更新接口时使用。覆盖污染入口识别、__globals__链构造、Flask SECRET_KEY/Jinja2定界符/searchpath污染、pydash路径过滤绕过、Sanic污染链、RCE/文件读取/权限提升利用

Sep 17
wgpsec Bundle

Deserialization Methodology

不安全反序列化漏洞利用。当发现 Base64 编码的 Cookie/参数、Python pickle 数据、PHP serialized 字符串(O:4:...)、Java serialized 数据(rO0AB...)时使用。可直接获取 RCE

Sep 17
wgpsec Bundle

Prototype Pollution Exploit

JavaScript 原型链污染漏洞利用方法论。当目标为 Node.js 应用、使用 lodash/jQuery/深拷贝函数、接收 JSON 输入时使用。覆盖 Server-side（RCE/权限绕过）和 Client-side（XSS/DOM 操控）两种场景

Sep 17
wgpsec Bundle

Command Injection Methodology

OS命令注入的检测、利用、盲注和输出绕过。当目标有Ping/Traceroute/DNS查询等网络工具、参数传入shell命令时使用。包含分隔符大全、输出过滤绕过策略、正则匹配伪造技巧

Sep 17
wgpsec Bundle

Java Deserialization Methodology

Java 反序列化漏洞检测与利用。当目标是 Java 应用（Tomcat/Spring/WebLogic/JBoss/Jenkins）、发现 rO0AB/aced0005 开头的 Base64 数据、HTTP 请求中有 application/x-java-serialized-object Content-Type、或存在 T3/IIOP/RMI/JNDI 协议端口时使用。覆盖 ysoserial gadget chain、JNDI 注入、Fastjson/Jackson 反序列化、Shiro rememberMe、常见中间件 CVE 利用

Sep 17
wgpsec Bundle

Information Disclosure Methodology

Web 应用敏感信息泄露检测与利用。当发现 .git/.svn 目录、备份文件路径(.bak/.zip/.tar.gz)、.env 配置文件、Swagger/OpenAPI 文档、debug 页面等信息泄露点时使用。也适用于发现源码泄露后的深入利用：git 历史审计（git log -p -S 搜索已删除的密码和 flag）、svn wc.db 文件列表提取、.DS_Store 目录枚举。优先于漏洞利用——信息泄露可直接提供凭据和攻击路径，往往比直接挖漏洞更快进入系统

Sep 17
ftshare-lab Bundle

Security Search

按名称、代码或拼音搜索标的。必填 --query，可选 --limit。接口：GET /api/v1/market/security/search/。

Sep 17
pixartseu Bundle

Test Master

Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation frameworks; analyzing coverage gaps; performance testing with k6 or Artillery; security testing with OWASP methods; debugging flaky tests; or working on QA, regression, test automation, quality gates, shift-left testing, or test maintenance.

Sep 17
pixartseu Bundle

Gdpr

GDPR compliance knowledge base - cookie audit, form consent, user rights, privacy checklist. Use when auditing GDPR compliance, implementing cookie consent, reviewing form data collection, or checking privacy requirements.

Sep 17
harzva Bundle

Elsevier Preprint Prior Publication

Elsevier Preprint Prior Publication: preprint status, prior conference version disclosure, simultaneous submission, and overlap audit.

Sep 17
tony Bundle

Gh Create Issue

Use when filing a GitHub issue for a bug, feature, audit, review finding, or investigated piece of work.

Sep 17
tony Skill

Create Issue

Use when filing a GitHub issue for a bug, feature, audit, review finding, or investigated piece of work.

Sep 17
26zl Skill

Security Comms

Security communications — one fact, many audiences

Sep 17
26zl Skill

Offensive OAUTH

OAuth 2.0 attack checklist: authorization code interception, redirect_uri bypass, CSRF on OAuth flow, state parameter abuse, open redirector chaining, token leakage via Referer, PKCE bypass, and scope escalation. Use when testing OAuth implementations in web apps or bug bounty. Use only for authorized security research, training, or assessment.

Sep 17
26zl Skill

Offensive Osint

Comprehensive OSINT methodology skill for offensive security, red team intelligence gathering, and bug bounty reconnaissance. Covers domain recon, email harvesting, social media profiling, GitHub/code leaks, Shodan/Censys enumeration, breach data lookup, employee profiling, infrastructure mapping, cryptocurrency tracing, geospatial intelligence, and AI-assisted analysis workflows. Use when performing reconnaissance against a target domain or organization, investigating a person or entity, tracing cryptocurrency flows, geolocating images or events, or building an attack-surface map. Use only for authorized security research, training, or assessment.

Audited Sep 17
26zl Skill

Offensive Z Wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting Z-Wave smart home devices (door locks, sensors, garage controllers) — common in mid-2010s smart home deployments still in production. Use only for authorized security research, training, or assessment.

Sep 17
26zl Bundle

Security Arsenal

Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.

Audited Sep 17
26zl Bundle

Variant Analysis

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.

Sep 17
26zl Bundle

Insecure Defaults

Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or analyzing environment variable handling.

Sep 17
26zl Skill

Offensive Fuzzing

Practical offensive fuzzing methodology covering target identification, fuzzer selection (AFL++, libFuzzer, Honggfuzz, Boofuzz, syzkaller), harness writing, corpus curation, mutation strategies, coverage measurement, and crash triage. Use when setting up or running fuzz campaigns against any target: file parsers, network protocols, kernel drivers, EDR engines, embedded firmware, or language runtimes. Use only for authorized security research, training, or assessment.

Sep 17
26zl Skill

Offensive GRAPHQL

GraphQL security testing checklist: introspection abuse, batching attacks, query depth/complexity DoS, field suggestion enumeration, IDOR via GraphQL, injection through arguments, authorization bypass. Use when assessing GraphQL endpoints in web app tests or bug bounty. Use only for authorized security research, training, or assessment.

Audited Sep 17
26zl Skill

Security Payloads

Use when you need a specific exploit payload — XSS, SQLi, SSTI, SSRF, XXE, file upload bypass, auth bypass, command injection. Points to PayloadsAllTheThings + SecLists/Fuzzing locations, plus inline canonical payloads for the most common cases. Triggers on "xss payload", "sqli payload", "ssti payload", "ssrf bypass", "xxe payload", "command injection".

Sep 17

Frequently asked questions

What are Security agent skills?

Which Security skills are most installed?

Popular Security skills on SkillMD right now include mongodb-attack, graphql-methodology, lfi-rfi-methodology. Rankings shift as installs change; sort this page by "Most installs" for the live list.

Do Security skills work with Claude Code and Cursor?

Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.