🛡️ 网络安全 · 渗透测试 · 攻防对抗 · 红蓝对抗 · AI Agent Skills
🛡️ Cybersecurity · Penetration Testing · Red/Blue Team · AI Agent Skills
中文 | English
██████╗ ███████╗████████╗██████╗ ██████╗ ██████╗ ██████╗ ███████╗██████╗ ██████╗ ███████╗
██╔════╝ ██╔════╝╚══██╔══╝██╔══██╗██╔═══██╗ ██╔══██╗██╔══██╗██╔════╝██╔══██╗██╔═══██╗██╔════╝
██║ ███╗█████╗ ██║ ██████╔╝██║ ██║ ██████╔╝██████╔╝█████╗ ██████╔╝██║ ██║███████╗
██║ ██║██╔══╝ ██║ ██╔══██╗██║ ██║ ██╔══██╗██╔══██╗██╔══╝ ██╔══██╗██║ ██║╚════██║
╚██████╔╝███████╗ ██║ ██║ ██║╚██████╔╝ ██║ ██║██║ ██║███████╗██║ ██║╚██████╔╝███████║
╚═════╝ ╚══════╝ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚══════╝
OpenClaw SecSkills 是一个专门为网络安全从业人员、渗透测试工程师、红蓝对抗团队整理的 AI Agent Skills 集合。
本项目基于 OpenClaw 框架，将传统安全工具与 AI Agent 能力相结合，让安全测试更智能、更高效。
| 🎯 | 🤖 | 🔧 | 📦 |
|---|---|---|---|
| 精准分类 | AI 驱动 | 工具集成 | 持续更新 |
| 8 大安全领域 | 智能自动化 | 集成主流工具 | 每周更新 |
| 200+ Skills | 自然语言交互 | Nmap/Nuclei 等 | 社区贡献 |
2026年最新 ChatGPT Plus / Grok / Claude 国内充值终极指南
🔥 实测有效 | ⚡ 3分钟到账 | 🛡️ 30天质保 | 💰 全网最低价￥149起
| 核心优势 | 说明 |
|---|---|
| 🎯 卡密式代充 | 无需信用卡，微信/支付宝/USDT 直接购买 |
| ⚡ 极速到账 | 自动发卡，3分钟内完成升级 |
| 🛡️ 正规渠道 | iOS 应用内购，非黑卡盗刷，无封号风险 |
| 💰 价格最低 | ￥149起，比市面所有代充都便宜 |
| 🧾 企业开票 | 支持企业发票，报销无忧 |
👉 立即前往充值： https://gptget.top （店铺：catfk.com）
📖 查看详细教程： GitHub 仓库
| 🛡️ ScanDomain — 免费在线子域名扫描神器 | 🚀 KvioAI — AI API 聚合平台，一个 Key 调用所有主流模型 | 💳 CatFK 代充 — ChatGPT Plus/额度代充，全网最低价 |
| 一键发现网站隐藏资产 · 子域名爆破 · 接管检测 · 指纹识别 | Claude / GPT / Gemini 一站式接入 · 国内直连 · 价格更优 | 绝对正规渠道 · 30天质保 · 比市面所有代充都便宜 |
| 👉 立即使用 | 👉 立即注册 | 👉 立即前往 |
Details
白盒代码安全审计，覆盖 Java/PHP/Python/智能合约等
| Skill | 描述 | 来源 |
|---|---|---|
| sast-skills | Scan codebases for security flaws with LLM agent skills — turn AI assistants into SAST scanners | github |
| securecoder | Installable AI-agent skill bundle for OWASP-driven code scanning, fixing, secure-build supervision | github |
| security-audit-system-skill | Structured security audit system for Claude agents — improve security practices on any repo | github |
| agent-skills | 100+ specialized AI agent skills — development, security, design, FinOps, compliance, testing | github |
| agent-skills | Agent skills for AI coding agents — Laravel, React, TypeScript, security, code quality, technical debt | github |
| nsauditor-ai-agent-skill | AI Agent Skill for NSAuditor AI — MCP tools, schemas, plugins, security audit workflows | github |
| Skill-Sonar | Protect AI agents with lifecycle security for pre-install checks and runtime monitoring | github |
| skills-scanner | Security scanner for AI agent skills, MCP servers, and agent harness configs | github |
| honeybadger | Security scanner for AI agent skills — detects secrets, CVEs, supply chain attacks, prompt injection in SKILL.md | github |
| skill-dfyx_code_security_review | 五阶段标准化审计协议，系统性发现安全漏洞 | github |
| whisper-skills | Agent Skills for WhisperGraph MCP — threat investigation, Cypher query authoring, brand-protection sweeps | github |
| security-hardening | Portable defensive application security skill — OWASP, MCP security, prompt injection, threat modeling | github |
| claude-active-directory | Active Directory offensive security AI agent harness — 8 skill domains, 13 slash commands, 7 agents | github |
| security-lab | AI-driven security testing toolkit: 37 skills, multi-agent pentesting, comparison framework for web apps and APIs | github |
| claude-security-skills | Defensive security skills for Claude Code — web applications and generative AI systems | github |
| skills | Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows | github |
| SlowMist-Learning-Roadmap-for-Becoming-a-Smart-Contract-Auditor | Smart contract audit skills roadmap for beginners, auditors, engineers, etc. | github |
| solsec | A collection of resources to study Solana smart contract security, auditing, and exploits. | github |
| Smart-Contract-Security-Audits | Certified Smart Contract Audits for Ethereum, Solana, Near, Cardano, Aptos, Sui, Binance Smart Chain, Fantom, EOS, Tezos | github |
| Smart-Contract-Auditor-Tools-and-Techniques | This repo contains a comprehensive list of smart contract auditor tools and techniques that can be utilized by both smar | github |
| SmartContracts-audit-checklist | A checklist of things to look for when auditing Solidity smart contracts. | github |
| smart-contract-audits | ContractWolf audited smart contracts | github |
| QuillAudit_Smart_contract_Auditor_Roadmap | Smart Contract Auditor Roadmap | Learn Blockchain Security & Smart Contract Auditing |
| smart-contract-auditing-heuristics | Heuristics for smart contract auditors | github |
| java-audit-skills | 专注于java代码审计skills | github |
| QuillAudit_smart_contract_audit_Reports | QuillAudits — Smart Contract Audits for DeFi, RWA, DEXs, Tokens, DeAI & DApps | github |
| PHP-Code-Audit-Skill | PHP-Code-Audit-Skill是一个专注于PHP代码审计的Skill | github |
| agentseal | Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks | github |
| wxmini-security-audit | 微信小程序全自动安全审计 Skill，基于 Claude Code Agent Teams。7 Agent 协作，覆盖敏感信息、API接口、加密分析、漏洞分析四大维度。采用脚本+LLM双层架构，脚本保证覆盖率，LLM保证准确率。 | github |
| claude-security-audit | Skill Claude Code pour audit de sécurité complet (OWASP Top 10, CWE/CVE, headers, auth, paywall, infra) | github |
| claude-cybersecurity | AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, 1 | github |
| panguard-ai | Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence a | github |
| PHP_AUDIT_SKILLS | PHP静态+动态+AI代码审计skills | github |
| solidity-auditor-skills | github | |
| claude-security-research-skill | AI-powered security research assistant for Claude Code — structured assessment workflows, tool orchestration, and profes | github |
| security-audit-skill | Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible |
| java-audit-skillss | java-audit-skillss | github |
| claude-skills | UX/UI evaluation, AI governance, and AI security skills for AI coding assistants. Audit interfaces with Nielsen heuristi | github |
| marketplace | Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified. | github |
| supabase-pentest-skills | 24 AI Agent Skills for professional security auditing of Supabase applications. Detection, key extraction, RLS testing, | github |
| skill-dfyx_code_security_review | 五阶段标准化审计协议，系统性发现安全漏洞 | github |
| Code Audit | 覆盖 55+ 漏洞类型，双轨审计模型，多 Agent 深度分析 | github |
| zh-audit-skills-hub | 中文用户代码审计 Agent Skills 仓库 | github |
| perseus | AI-powered security assessment SKILLS for codebase. Multi-language | github |
| full-stack-audit | 90-point full-stack audit skill for websites and web apps. Catches security holes, accessibility issues | github |
| sentinelai | Security scanner, cost tracker, and model router for the AI ecosystem | github |
| trivy-security-agent-skill | AI-powered Trivy security scanning skill for Claude Code | github |
| dependency-scanner | Claude Code skill that scans npm/pip dependencies for vulnerabilities | github |
自动化渗透测试、漏洞挖掘、Bug Bounty
| Skill | 描述 | 来源 |
|---|---|---|
| iothackbot | IoT HackBot: A collection of Claude Skills and custom tooling for hybrid IoT pentesting | github |
| Android-Pentesting-Checklist | Delve into a comprehensive checklist, your ultimate companion for Android app penetration testing. Identify vulnerabilit | github |
| labs-pentest | Free Labs to Train Your Pentest / CTF Skills | github |
| threat-modeling | AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assess | github |
| communitytools | Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunting, and s | github |
| awesome-claude-skills-security | Security testing toolkit for Claude Code: curated SecLists wordlists, injection payloads, and expert agents for authoriz | github |
| public-skills-builder | Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no private r | github |
| BugHunterMethodology | A comprehensive bug bounty methodology compiled from extensive research, covering web application reconnaissance, checkl | github |
| pentest-skills | 💬 🚀 告别繁琐命令行，用自然语言驱动专业级渗透测试。 ⚡ 让安全测试从未如此简单、高效。Forget complex command lines. 🛡️ Professional penetration testing, powered | github |
| OneLinerBounty | OneLinerBounty is a collection of quick, actionable bug bounty tips in one-liner format. Perfect for bug hunters looking | github |
| SecToolkit | Welcome SecToolkit repository! This is a comprehensive collection of cybersecurity and bug bounty hunting topics. Here, | github |
| picocom-claude-skill | A Claude Code skill for using picocom to give access to a live UART shell for enumeration, pentesting, etc. | github |
| VulnBox | VulnBox is a container that is intentionally designed with vulnerabilities to allow security professionals to practice a | github |
| Active-Directory-Workbook | A comprehensive and hands-on workbook designed to sharpen your Active Directory penetration testing skills. Whether you' | github |
| pentester-skills | 坤式网络安全学习法，不只是学习路线还是笔记。 | github |
| KaliPAKU | KaliPAKU is a training tool for penetration testing using Kali Linux. It is designed to help security professionals and | github |
| secknowledge-skill | 88,636 个真实漏洞案例 + 5,600+ 篇安全研究文档知识库 | github |
| Security Auditor | OWASP 十大审计、CORS/CSP 配置、SQL 注入/XSS 防护 | github |
| Pentest Api Attacker | OWASP API 安全前十名测试 | github |
| Pentest Auth Bypass | 身份验证绕过和账户接管测试 | github |
| claude-code-pentest | 6 skills that automate the entire pentest lifecycle. From recon to exploitation | github |
| Anthropic-Cybersecurity-Skills | 754 structured cybersecurity skills for AI agents, mapped to MITRE ATT&CK, NIST, OWASP | github |
| claude-forge | Supercharge Claude Code with 11 AI agents, 36 commands & 15 skills | github |
| pownie | Agent harness for offensive security. Plugin for Claude Code packed with skills, memory, rules | github |
| pentest-skills | 自动化渗透 agent skills | github |
| pentestagent | AI agent framework for black-box security testing — bug bounty, red-team, penetration testing | github |
| Zen-Ai-Pentest | AI-Powered Penetration Testing Framework — automated vulnerability scanning, multi-agent system, compliance reporting | github |
| CyberStrike | AI-powered offensive security agent with 7,300+ actionable security skills — MITRE ATT&CK, CIS Benchmarks, OWASP, NIST | github |
| ultraship | Claude Code plugin — 39 skills including pentesting, safety guardrails, canary monitoring, code review | github |
| kali-pentest | Kali Linux penetration testing skill for AI agents — 200+ CLI tools, 15 scenario playbooks, attack path planning | github |
| Threatswarm | 27 scope-enforced AI agents running full pentest kill-chain (recon→exploit→post-ex→DFIR→report), 754 MITRE-m |
... [OUTPUT TRUNCATED - 3188 chars omitted out of 53188 total] ...
/ctf-skills) | | reverse-skills | Reverse engineering skills for Claude Code | 逆向工程 Claude Code Skills 插件 | github | | Incident-Response-Projects-for-Beginners | Hands-on cybersecurity projects to enhance skills in phishing investigation, malware analysis, network intrusion detecti | github | | jshook-skill | AI-powered JS reverse engineering: deobfuscation, crypto detection, CDP debugging, hook injection, anti-detection | | github | | Common-CTF-Challenges | Common CTF Challenges is a collection of tools and resources to help individuals improve their Capture the Flag (CTF) sk | github | | IDA-Skill | 使用skill让 AI Agent 像安全分析师一样分析恶意样本 | AI Agent skill for automated malware analysis using IDA Pro | github | | spider-king-skill | Protocol-first reverse engineering skill for turning hostile web clients into pure-protocol Python collectors. | github | | ghidra-re-skill | Codex Ghidra reverse engineering skill with headless workflows, bug-hunting bundles, and a live bridge for Apple Mach-O | github | | CrackMaster | CCrackMaster is an educational CrackMe project written in C, designed to enhance skills in reverse engineering, code ana | github | | malware-analysis-claude-skills | Complete Claude skills toolkit for professional malware analysis. 5 specialized skills covering triage, dynamic analysis | github | | DeepExtractRuntime | AI-driven agent runtime for Windows PE binary analysis. Turns IDA Pro decompiled code and SQLite databases produced by D | github | | my-claude-skills | Binary analysis plugins for Claude Code: angr (static analysis, symbolic execution) and Frida (dynamic instrumentation) | github | | BloodCodeCTF | Blood Code CTF challenge repository! This repository contains all the challenges and their source files from the Capture | github | | TimeCod | KotlinCrackMaster is an educational CrackMe project written in Kotlin, designed to enhance skills in reverse engineering | github | | hello_js_reverse_skill | JS 逆向与爬虫对抗，Camoufox 反检测浏览器 | github | | JS Reverse MCP | JavaScript 逆向工程 MCP 服务器 | github | | FlowDroidSkill | APK 静态污点分析，检测数据泄露路径 | github | | re-skill | Claude Code skill for reverse engineering retro games — disassemble, annotate, explore | github | | epistemic-deconstructor | Claude skill for reverse engineering systems | github | | android-reverse-engineering-claude-skill | Decompile Android APK, XAPK, AAB, DEX, JAR using jadx | github | | apple-silicon-internals | Reverse engineering toolkit for Apple Silicon private APIs. 55+ frameworks | github | | iOS-reverse-engineering-claude-skill | Claude Code skill for extracting, analyzing, reverse engineering iOS apps | github |
| Skill | 描述 | 来源 |
|---|---|---|
| 『逆向资源区』 - 吾爱破解 - 52pojie.cn | 1 天前 · 『逆向资源区』 收录了在逆向过程中会使用的绝大多数工具，工欲善其事必先利其器，好的工具在逆向破解工程中起到事半功倍的作用。 本区根据工具的作用分成以下几类，分别做以中文解释说 … | 吾爱破解 |
CTF 解题技巧、工具使用、漏洞挖掘
| Skill | 描述 | 来源 |
|---|---|---|
| ctf-practice | Practice your hacking skills with these CTFs | github |
| linux-ctfs | A collection of Linux CTFs to practice your CLI skills | github |
| SecSkills | 收集整理渗透测试、漏洞扫描、代码审计、CTF、逆向、安全研究 等网络安全相关的 Skills和MCP | github |
| Walkthrough-and-Writeup | Welcome to my Capture The Flag (CTF) Walkthroughs & Writeups Repository. This repository contains educational, step-by-s | github |
| android-h1 | 基于 HackerOne 真实报告的移动安全漏洞挖掘 | github |
| BugBounty-Hunting | 漏洞赏金猎人资源集合 | github |
安全风险评估、威胁分析、合规检查
| Skill | 描述 | 来源 |
|---|---|---|
| ThreatHunt | ThreatHunt is a PowerShell repository that allows you to train your threat hunting skills. | github |
| SOC-Analyst-Notes | Comprehensive SOC Analyst notes covering incident response, threat hunting, SOC workflows, and cybersecurity concepts—pe | github |
| SkillWard | Security scanner for Agent Skills — uncover hidden threats before deployment. | github |
| cti-expert | CTI Expert — Cyber Threat Intelligence & OSINT analysis skill for Claude Code. 67+ commands, 35 techniques, no API keys | github |
| 30-Day-SOC-Analyst-Challenge | A 30-day hands-on SOC Analyst project simulating real-world cyber attacks using ELK Stack, Mythic C2, osTicket & Elastic | github |
| Offensive-Security-Forensics-Portfolio | A portfolio demonstrating advanced blue and red team skills, including: SSH MFA implementation, Volatility-based memory | github |
| ghsa-skill-builder | 自动将 GitHub 漏洞库和 HackerOne 报告转化为 Skills | github |
Android/iOS 安全分析、漏洞挖掘
| Skill | 描述 | 来源 |
|---|---|---|
| Damn-Vulnerable-Bank | Damn Vulnerable Bank is designed to be an intentionally vulnerable android application. This provides an interface to as | github |
| Skill-Android-Security-Agent | 构建基于 Skill 的 Android 智能审计 Agent | github |
| mobile-security-learning-resources | This repository contains list of mobile security related resources that you can use to learn new skills and test existin | github |
| mobile-challenges | This repository houses diverse files and challenges centered around Just Mobile Security. With practical exercises and r | github |
| android-reversing-challenges | there are some CTF challenges or some other things helping improving android reversing skills. | github |
安全事件响应、取证分析、日志分析
| Skill | 描述 | 来源 |
|---|---|---|
| aguara | Security scanner for AI agent skills and MCP servers. Static analysis, incident response, no LLM. One binary. Detectio | github |
| repo-forensics | Automated Security scanner for GitHub repos, Agent Skills, Plugins, and MCP servers. 18 scanners. Zero dependencies. Kee | github |
| Digital-Crime-Scene-Challenge | The object of the Digital Crime Scene Challenge is for participants to use their forensic and investigative skills to fo | github |
| mini-hids | 轻量级主机入侵检测与日志分析系统，支持封装为AI Agent Skill。/ A lightweight HIDS for Linux, featuring AI-powered log analysis and automated def | github |
| backdoorsandbreaches-socinvader | 🎮 AI-powered solo mode for Backdoors & Breaches. Train incident response skills anytime with an LLM Incident Master. Arc | github |
| Digital-Forensic-Training | The Chupacabra case study was created by the ADEO dfir team due to the lack of resources and applications in the digital | github |
| DevOps-Security-Agent-Skills | Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform | github |
| agent-infra-security | Security skills for AI coding agents — incident response for supply chain attacks, credential rotation, IOC detection. W | github |
| LinuxGun-skill | Linux 安全应急响应 AI 检查 | github |
| Email-OSINT | 自动化电子邮件 OSINT 工具 | github |
| incident-report-skill | Taiwan cybersecurity incident report generator | github |
| SecOpsAgentKit | Security operations toolkit for AI coding agents. 25+ skills for CVE research, exploit dev, threat intel | github |
| dfir-skills | DFIR/SOC skillset for Claude Code — memory forensics, log analysis, network forensics | github |
扫描器、漏洞利用、红蓝对抗工具、AI 安全
| Skill | 描述 | 来源 |
|---|---|---|
| raptor | Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating r | github |
| slowmist-agent-security | SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environm | github |
| secureclaw | SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned | github |
| SecurityClaw | A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, bu | github |
| faillapop | Vulnerable-by-design solidity protocol to help Web3 security enthusiasts practice their skills in an environment closer | github |
| claude-code-owasp | Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, an | github |
| www-project-agentic-skills-top-10 | OWASP Foundation web repository | github |
| web3-bug-bounty-hunting-ai-skills | 18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack reproductions, | github |
| kernel-vuln-analyzer | Claude Code skill for Linux kernel vulnerability analysis — from crash log triage to patch verification | github |
| CEH-Assessments | A structured portfolio of weekly CEH v13 assessments, vulnerability labs, and ethical hacking documentation to demonstra | github |
| MalwareAnalysis | This central repository is crafted for cybersecurity enthusiasts, researchers, and professionals aiming to advance their | github |
| red-team-blue-team-agent-fabric | 466 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply ch | github |
| mobile-security-skills | A collection of Claude Code and OpenAI Codex Agent Skills for mobile application security testing | github |
| htb-writeups | The most comprehensive Hack The Box writeup collection - 500+ machines, 400+ challenges, interactive knowledge graph, sk | github |
| tirith | Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated pay | github |
| agentguard | Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runti | github |
| SOC-Ressources | Repository for SOC analysts, queries to investigate, advanced hunting, sites for analysis, malware samples, courses to i | github |
| security-skills | A collection of Claude Code skills that help security teams stay secure | github |
| cybersecurity-skills | Cybersecurity skills for AI coding agents (Claude Code, Cursor, Codex) | github |
| AI-agent-master-cyber-skills-list | Comprehensive cybersecurity skill pack for AI coding agents — 741 skills | github |
| awesome-ai-agent-skills | 70+ ready-to-use, platform-agnostic AI agent skills | github |
| Awesome-OpenClaw | A carefully curated list of awesome OpenClaw resources | github |
| Skill | 描述 | 来源 |
|---|---|---|
| ANYDESK-BACKDOOR | You should never use malware to infiltrate a target system. With the skill of writing and exploiting technical codes, yo | github |
| PayloadsAllTheThings | Web 安全 payload 和绕过列表 | github |
| BugBountyGuide | 漏洞赏金绕过技巧和 payload | github |
| Skill | 描述 | 来源 |
|---|---|---|
| Red-Team-Roadmap | Red Team Roadmap [defination, job positions, skills, tools] | github |
| eJPT | eJPT is a hands-on, entry-level Red Team certification that simulates skills utilized during real-world engagements. | github |
| Red-Team | 红队/渗透测试工具集合 | github |
| Windows-Exploits | Windows 提权漏洞集合 | github |
| AD-Attack | Active Directory 攻击路径 | github |
| Pentest Active Directory | AD 身份攻击路径评估 | github |
| Skill | 描述 | 来源 |
|---|---|---|
| pydantic-ai-shields | Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction | github |
| AgentForensics | Monitors LLM agent sessions in real time — detects prompt injection across tool outputs, web pages, documents | github |
| immunity-agent | Security for AI agents — block dangerous commands, prevent secret leaks, enforce runtime policies across all major agents | github |
| agentshield | AI agent security scanner — detects vulnerabilities in agent configs, MCP servers, tool permissions. CLI + GitHub Action | github |
| hol-guard | AI antivirus for developer agents — protect Codex, Claude Code, Cursor, plugins, skills, MCP servers before tools run | github |
| sandboxed.sh | Safe runtime for autonomous on-chain AI agents — isolated sandboxes, encrypted secrets, OKX read-only security checks | github |
| kontext-cli | Runtime Security for tool-using AI agents — permissions, credentials, policy enforcement, audit trails | github |
| skillguard | Security scanner for AI agent skills — detects prompt injection, data exfiltration, malicious payloads | github |
| agent-bom | Open security scanner for AI supply chain — agents, MCP, containers, cloud, GPU, runtime with blast-radius analysis | github |
| lang-guardx | Adaptive security for LangChain apps — blocks prompt injection, validates tool calls, filters malicious outputs | github |
| ai-security-lab | AI/LLM Security Testing Framework — 50+ jailbreak techniques, prompt injection tools, automated vulnerability scanners | github |
| skillscan-security | Security scanner for AI agent skills and MCP — prompt injection, IOC matching, malware detection, ML classifier | github |
| ai-shield | LLM security toolkit — prompt injection detection, PII masking, cost tracking, tool policies. <25ms scans | github |
| llm-audit | OWASP LLM Top 10 vulnerability scanner CLI — prompt injection, jailbreaks, data leakage, with fix recommendations | github |
| lochbot.com | Prompt Injection Vulnerability Checker — 31 attack patterns across 7 categories, security scoring | github |
| yula | Production-ready CLI for adversarial red-teaming of AI systems — prompt injection, jailbreaks, evasion techniques | github |
| llm-red-teamer | Automated prompt injection & jailbreak testing — OWASP LLM Top 10, 43 real-world payloads, risk scoring | github |
| openclaw-skill-vetter-mcp | MCP server for security-vetting AI agent extensions — 41 detection rules, 0-100 risk score | github |
| llm-security-test | LLM Security Test — AI Safety Evaluation Tool for Jailbreak, Prompt Injection, Harmful Content Detection | github |
| ai-security-toolkit | LLM security research toolkit — jailbreak detection, prompt injection testing, adversarial text generation, API fuzzing | github |
| Skill | 描述 | 来源 |
|---|---|---|
| ramibot | RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s | github |
| Skill | 描述 | 来源 |
|---|---|---|
| CLS-Certify | Skill 安全检查工具 | github |
| SkillGuard | OpenClaw Skill 安全检查 | github |
| skill-audit | 审计 Skill 定义的安全性、完整性 | github |
| Skill | 描述 | 来源 |
|---|---|---|
| agent-scan | Security scanner for AI agents, MCP servers and agent skills. | github |
| skill-scanner | Security Scanner for Agent Skills | github |
| nova-proximity | Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA | github |
| llm-sast-scanner | A SAST skill that gives AI coding agents structured vulnerability detection across 34 vulnerability classes. | github |
| claude-skill-antivirus | Security scanner for Claude Code Skills — 9 engines detect malicious patterns, data exfiltration, dangerous ops across 7 | github |
| skillsentry | AI Skill Security Scanner | github |
| skillcheck | Security scanner for Claude SKILL.md files. Detects vulnerabilities before they reach production. | github |
| SkillSemgrep | 基于 Semgrep 的自然语言漏洞扫描 | github |
| Nmap | 网络发现和安全审计 | github |
| Nmap Pentest Scans | Nmap 主机发现、端口枚举、NSE 分析 | github |
| Security Scanner | 集成 nmap、nuclei 的自动化扫描 | github |
| Nuclei | 基于模板的快速漏洞扫描器 | github |
| scv-scan | Claude Code skill that scans Solidity codebases for security vulnerabilities | github |
| redhound-arsenal | 76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics | github |
| Skill | 描述 | 来源 |
|---|---|---|
| reconFTW | 自动化侦察工具 | github |
| Skill | 描述 | 来源 |
|---|---|---|
| AI-Infra-Guard | 全栈 AI 红队测试平台 — OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, LLM jailbreak 评估 | github |
| pentestagent | AI agent framework for black-box security testing — bug bounty, red-team, penetration testing | github |
| Zen-Ai-Pentest | AI-Powered Penetration Testing Framework — automated vulnerability scanning, multi-agent system | github |
| agentic_security | Agentic LLM Vulnerability Scanner / AI red teaming kit | github |
| agent-security-scanner-mcp | Security scanner MCP server for AI coding agents — prompt injection firewall, 1000+ vulnerability rules, AST & taint analysis | github |
| LLMrecon | Enterprise-grade LLM security testing framework — OWASP LLM Top 10, advanced prompt injection, jailbreak | github |
| WonderSuite-Ai-Bug-Bounty | AI-Powered Offensive Security Research Engine — 90 tools, MITM proxy, stealth browser, autonomous AI agent | github |
| agent_asteroid | Agent responsible for detecting remote vulnerabilities, a robust scanner | github |
| DVAI | Damn Vulnerable AI — hands-on AI security training across 12 categories, OWASP LLM Top 10, works 100% offline | github |
| CyberStrike | AI-powered offensive security agent with 7,300+ actionable security skills — MITRE ATT&CK, CIS, OWASP, NIST | github |
| Threatswarm | 27 AI agents running full pentest kill-chain backed by 754 MITRE-mapped skills | github |
| Skill | 描述 | 来源 |
|---|---|---|
| supply-chain-defense-skills | Reusable Security Skills for AI Coding Agents — protect against supply chain attacks in npm, PyPI, etc. | github |
| DevOps-Security-Agent-Skills | 80+ DevOps security skills — Kubernetes, Terraform, AWS/Azure/GCP, container hardening, SOC2/ISO27001, incident response | github |
| Skill | 描述 | 来源 |
|---|---|---|
| Best-LwM2M-Agentic-Skills | Worlds most comprehensive OMA LwM2M (IoT) expert skill for Claude | github |
| Claude-Code-CyberSecurity-Skill | Comprehensive collection of 15 Claude Code Skills for cybersecurity | github |
网络安全学习资源、练习平台、知识框架
| Skill | 描述 | 仓库 |
|---|---|---|
| 1earn | ffffffff0x 团队安全知识框架：Web/工控/取证/应急/后渗透 | GitHub |
| Awesome-Infosec | 信息安全课程和培训资源精选 | GitHub |
| HackTheBox | CTF 和渗透测试练习资源 | GitHub |
| 工具 | 描述 | 链接 |
|---|---|---|
| ScanDomain | 🔥 免费在线子域名扫描神器 — 一键发现隐藏资产、子域名接管检测、网站指纹识别，渗透测试前必备信息收集工具 | 立即使用 → |
| KvioAI | 🚀 AI API 聚合平台 — 一个 Key 接入 Claude/GPT/Gemini 等 50+ 主流模型，国内直连无需翻墙，价格比官方更优 | 立即注册 → |
| CatFK 代充 | 💳 ChatGPT Plus/额度代充 — 绝对正规渠道，30天质保，比当前市面所有代充都便宜，安全无忧 | 立即前往 → |
我们欢迎所有网络安全从业者的贡献！
- Fork 本仓库
- 创建新分支 (
git checkout -b feature/AmazingFeature) - 提交更改 (
git commit -m 'Add some AmazingFeature') - 推送到分支 (
git push origin feature/AmazingFeature) - 开启 Pull Request
请在 PR 中按以下格式提供信息：
## Skill 名称
- **描述**: 一句话描述功能
- **仓库链接**: GitHub URL
- **分类**: 代码审计/渗透测试/逆向工程/...
- **标签**: #java #audit #security