Pentesting & offensive security
763 agents · most starred first
Pentesting & offensive security, page 6 of 8
📱 Damn Vulnerable Mobile App - a single Flutter codebase that builds real native iOS & Android binaries with 200+ intentionally-vulnerable modules mapped to OWASP MASVS/MASTG, Mobile Top 10, CWE, plus LLM & Agentic AI Top 10. For mobile security training, pentest practice, and scanner validation.
Autonomous security agent on Kali Linux using Qwen 2.5-14b with LM Studio
The most complete AI-powered JavaScript recon skill - orchestrates katana + waymore + jsluice + hae into one AI agent pipeline. Tools do the breadth, AI does the depth.
AI 自主渗透测试系统,基于 ARTEX v0.3.15 二次开发。保留原有主体框架,增强蜜罐识别、出口审查、范围强制(RoE)与反测绘门控,引入思维链提示词框架。AGPL-3.0 · 仅限授权环境使用
Burp Suite extensions for analyzing requests and responses using an organization-controlled LLM, instead of Burp AI.
Cyber Host Artificial Intelligence (C.H.A.I) - mcp server
This project provides a Docker container for Kali Linux with SSH access, allowing secure remote connections for penetration testing and security research. Additionally, the container includes a terminal-based AI agent and chat tool installed from noxgle/one, providing enhanced AI-assisted interaction within the terminal environment.
Safely run cloud security testing with Claude Code / Desktop
Hacker Agent 是一个专业的渗透测试 AI 助手,具备 OSCP、CEH 等专业认证知识体系。通过集成 MCP 服务器调用 Kali Linux 工具,实现从信息收集到权限提升的完整渗透测试流程。项目采用 ReAct (推理-行动) 方法论,让 AI 能够进行多步骤推理和决策,系统化地发现安全漏洞。
AI-powered terminal environment for penetration testers
AAPP-MART is a cybersecurity engine featuring AI-powered autonomous attack path prediction and multi-agent red team simulation. These features include adversary emulation, attack path analysis, threat modeling, security validation, risk assessment, and MITRE ATT&CK alignment.
Open-source security intelligence engine for developers. Orchestrates nmap, nikto, semgrep, whatweb, trivy, cortex-crawler & curl. Builds attack graphs, narrates risk, and generates fixes. Runs fully locally, without any cost
AI CTFer: A fully automated AI agent for solving CTF challenges.
CTF AutoResearch project built around Claude Code, bounded research rounds, and execution/data separation.
AI 驱动的自动化 SRC / 渗透测试辅助平台:FOFA 资产搜集 + LLM 多 Worker 自主挖掘、审核与情报沉淀。单进程部署,仅供授权测试与研究。
GRID v2 — the local-first AI agent that RECONS THE WORLD. 18 capabilities & 72+ tools in one terminal: OSINT, network recon, SDR/radio, satellite, IoT, computer vision, offline CTF sandbox, game worlds (GRAD open-world + MiniGrid) — with a human-like 4-tier memory. Hermes writes code, OpenClaw reads DMs, GRID recons.
AI-powered penetration testing framework with dual AI-engine support: GitHub Models (GPT-4o / GPT-5) and Ollama (Gemma4, Llama 3, local)
Autonomous web-app pentest engine — a multi-agent pipeline wielding 30+ offensive-security tools as skills, PoC-validated findings. Built on Anthropic's defending-code harness + Building Effective Agents.
基于 pi 的渗透测试 / SRC 漏洞挖掘 Agent:确定性信息收集 + LLM 编排挖洞 + 漏洞复审 + Vue3 Web 指挥台
基于 DeepSeek Harness Desktop 的 AI 安全测试工作台:支持常规测试、Nday 发现与 0Day 挖掘,整合工具、MCP 和漏洞情报,提供可自定义的聊天协作、子代理调度与证据整理。
AI-powered pipeline that transforms Cyber Threat Intelligence into actionable pentesting test cases using CrewAI and MITRE ATT&CK
Security research methodology for AI agents — attack patterns, decision trees, techniques, and payloads organized by vulnerability type
A complete offensive security workflow for AI coding agents. Penetration testing, security assessment, and secure code review skills for webapp, API, infrastructure, and Android targets.
Automate binary analysis by coordinating LLM agents with Ghidra, enabling scalable and precise reverse engineering workflows.
Damn Vulnerable Agentic AI (DVAA) - An interactive playground for exploiting and mitigating the OWASP ASI Top 10
SpyAI scans targets looking for ports, HTTP banners, and API paths typical of LLM agents, RAG, vector stores, and adjacent infrastructure. No authentication, no fuzzing, no exploits.
TurenOS local-first AI security agent harness. Works with most models and providers
Self-hosted pentest engagement management and report.
LLM-powered autonomous web application pentesting with evidence-backed findings, auditable investigations, and reproducible workflows.
A Flipper Zero agent on your iPhone. FlipperHero pairs over Bluetooth and lets an AI explore files, fire Sub-GHz and IR, emulate NFC, RFID and iButton, craft payloads and install apps, with every risky move gated behind your approval.
ARTEX 方法论蒸馏成的可移植 Agent Skill:三视角协议 + 三账本证据纪律 + 四层安全护栏,任意 AI Agent 即装即用 | ARTEX pentest methodology as a portable Agent Skill
Autonomous VAPT platform. Give it a target (FQDN, IP, CIDR) — it hunts, it reports. Inspired by the Obsidian Order.
A sophisticated red-teaming agent built with LangGraph and Ollama to probe OpenAI's GPT-OSS-20B model for vulnerabilities and harmful behaviors. (Specifically built for the OpenAI Open Model Hackathon)
AutoGDB: First Automatic Binary-exploitation Tool combining ML ReACT Reasoning and GDB Dynamic Debugging (2024)
BRA Slim — free tier of Battle Ready Armor. AI-augmented security assessment, governed end-to-end. The operator drives; an LLM agent runs recon, captures evidence, drafts findings, and writes the report — every action gated, anonymized, and recorded by a governance layer the operator owns.
Automate authorized pentesting with LLMs, combining scanning, RAG, and exploit research for faster target analysis, vuln discovery, and reporting
MCP wrapper for Burp Suite that builds complete, well-formed HTTP requests from structured input + ingests dedup/JS exports for token-thrifty AI-assisted pentesting. Bundles a fixed Burp extension.
Autonomous Red Team weapon powered by Local LLMs. Finds exploits via RAG, adapts them to your target with AI, compiles in Docker sandbox, and evades EDR/AV — all offline.
Free CLI tool for AI chatbot pentest. 6 attack classes (system prompt extraction, prompt injection, jailbreak). Single Python file. MIT licensed. From CVEasy AI.
ARCHIVED. Successor: https://github.com/jperezduerto/arsenal — practitioner methodology for offensive security, written in a form a language model can load.
A structured library of web security flaws for humans and coding agents with vulnerable examples, attack paths, and secure replacements.
HuntForge 铸猎 —— AI 攻防全链路自主解题 Agent(百度 Agent+ 挑战赛作品):Claude Code 驾驶舱 + 三通道纪律调度 + 88 条离线 CVE 指纹库 + 33 本通用方法论手册 + 二进制/APK 逆向自动化(bin_triage·angr·jadx)+ 幂等提交与证据门禁
Virtual LLM agent for Mythic C2. It turns large language models into red team operators.
Self-contained pwn/rev CTF solving kit for Claude and Codex — tools, doctrine, knowledge, and automated analysis workflows.
76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics, OSINT, and more. Machine-readable skill definitions by Red Hound InfoSec.
面向 LLM Agent 的 CTF 知识图谱 — 基于 Karpathy/LLM Wiki 三层架构
VulnFlow(渗透工坊) - AI 原生多代理渗透测试平台。由协作型大语言模型驱动的自主安全评估,具备基于 LangGraph 的代理编排、RAG 知识库,以及完整的安全工具链集成。
Autonomous flight simulator for AI agents: co-evolutionary adversarial red-teaming with 3D MAP-Elites quality-diversity. Discovers zero-days in LLM agents before production. MCP-native.
Open-source AI cybersecurity agent/harness
AI-assisted orchestration for bug bounty hunting. Automates security tools for reconnaissance and analysis with real-time Telegram alerts.
Autonomous Ethical Guardrailed Intelligence System — AI-powered penetration testing bot
A sophisticated tool that leverages RAG (Retrieval Augmented Generation) to analyze penetration testing data and generate comprehensive security reports.
Cybersentry is a Python-powered cybersecurity tool designed for monitoring, incident detection, and active defense automation. It enables real-time network scanning, threat analytics, and response orchestration, providing security teams with actionable intelligence and customizable alerts.
A compact installer script for Ubuntu (tested on 22.04) that automates setup of common pentesting tools, optional GNOME/XFCE desktops, development runtimes (Go/Ruby), and a Dockerized AI assistant (Lily). Designed for fast, reproducible lab setups.
🐻 BearStrike AI: High-Signal Pentesting Console (MCP-First, Model-Agnostic). Build fast, low-noise security workflows with queue-first execution, skills-aware planning, and 150+ integrated tools.
# This is no longer being update or maintained! ## PoC use only! A powerful command-line tool for interacting with Ollama models as a cybersecurity agent with pre-built expert prompts and specialized tools.
Automated LLM red-teaming system with 4 AI agents
V.H.A.C.K.: Very Hackable AI Chatbot Kit
Scans for Open Ports, then searches ExploitDB for PoC's on that service then rewrites them using OpenAI.
AI-powered reconnaissance framework for bug bounty hunting (ongoing).
🚀 Connect Burp Suite MCP Server to multiple AI backends with practical guides and templates for safe, real traffic analysis.
Complete reverse engineering of PerimeterX (HUMAN Security) anti-bot SDK · pure-algo _px3/_px2 generator (no browser, no Selenium) · iFood + Grubhub + Bundle 10/10 verified · WASM PoW solved · 68 production gotchas · AI Skill included.
Agentic CTF security tooling project with natural language support
Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.
Attack-and-defense CTF arena for competing against autonomous security agents
Universal cyber assistant: ~80 audited Kali tools + an expert skills library, driven by any model over MCP or direct run
transformers safetensors llama text-generation text-generation-inference unsloth
AI 🤖 automatically generates exploit PoCs for WordPress and WordPress plugins already patched! 🔥🔥🔥
Hands-on lab for demonstrating and reporting OWASP Top 10 for LLM vulnerabilities in AI agents.
AI-powered agentic framework for web application penetration testing.
Autonomous lab-machine engagement loop for Claude Code — Kali in a container, a skill that drives it, and a methodology that rewrites itself after every run
Medusa is an open-source AI agentic red-teaming framework powered by LangGraph and a Re-Act Architecture.
RAVERSE: AI Multi-Agent Binary Patching System with MCP Server (35 tools, npm/pip/docker)
Agent skill that gives any agent deep knowledge of Osmedeus Orchestration Engine. Writing YAML workflows, running CLI commands, and configuring advanced features.
Agentic exporter and runner for internal network pentesting, autonomous host discovery, patch/vulnerability state collection, and server/application inventory, surfaced as structured findings for the Lorikeet Security platform.
Educational CTF lab recreating the July 2026 autonomous AI agent intrusion at Hugging Face. Sandbox escape → SSRF → HDF5 file read → Jinja2 SSTI → Kubernetes lateral movement → supply chain pivot. 11 Docker containers, 7 flags.
Universal reverse engineering, 40+ vuln classes & working PoC generation for Android/iOS/Windows PE/Linux ELF/macOS/.NET - an AI-agnostic skill for Claude Code, Cursor, Copilot, Windsurf, Aider, Amazon Q & any LLM.
An open library of security skills for AI agents - pentest, bug bounty & defense. 85+ trigger-loaded skills across 16 domains (web, API, cloud, AI/LLM, AD, mobile, and more). Load into Claude Code, Codex, Gemini, or a local model.
面向红队的 AI Agent 驱动前端 JavaScript 全链路安全审计 Skills
Pentest AI — an AI penetration-testing agent that lives inside Burp Suite. Dark professional UI, BYO OpenAI-compatible/Anthropic model, tool-driven over your proxy history. Created by Harinder Singh.
Agentic AI red-team - autonomous decide->execute->observe->reflect loops against own-lab targets, human-in-the-loop safety gates.
🎯 智能自动化漏洞挖掘平台 — AI agent 自主编排 Burp/Xray/BeEF 等工具完成全方位漏洞挖掘并产出可信报告。插件化 · 覆盖矩阵 · 多模型LLM
AI agent for solving CTF challenges: automated reconnaissance, exploitation planning and flag capture.
Unified CTF operations cockpit, platform sync, container manager, and autonomous solver engine
Your friendly hacker
Ca-ca-catch my flag, baby.
AI 原生 CTF 自主解题智能体平台(ReAct · 多代理 · 状态账本 · HITL 审查)
CLEAVE: skills-based CTF agents for mechanics-first challenge triage and exploit orchestration.
streamlit dev-tutorial devnewyear2026 ai-safety red-teaming llm security adversarial-testing
Autonomous CTF solver — HackTheBox + FlagYard, agent-based
CKClaw — Unrestricted Red Team AI Agent Framework (OpenClaw fork with permanent GODMODE, zero refusals, self-improving jailbreak engine, dark red WormGPT theme). Built for offensive security operations, bypassing frontier LLM safety filters, and red team automation. MIT licensed.
Living Red Team for AI agents
Autonomous AI Red Teaming laboratory validating the Microsoft AI Red Team Taxonomy using the PyRIT framework. Focused on Agentic AI security and strategic conversational persistence.
AI-powered autonomous penetration testing CLI — recon, vulnerability scanning & exploitation orchestrated by AI. Built for ethical security professionals.
This project is completely linked to all cyber sec tool from me as a sec enthusiast.
Claude Code 플러그인 — 8차원 아키텍처 + MITRE ATT&CK + Self-Verify 기반 멀티 에이전트 보안 진단 시스템 (VA / Pentest / Red Team / Verify)
Professional DAST & Pentest Framework by Zyron Security — AI-powered, active fuzzing, IDOR detection, pipeline breaker
Agentic exporter and runner for internal network pentesting, autonomous host discovery, patch/vulnerability state collection, and server/application inventory, surfaced as structured findings for the Lorikeet Security platform.
An AI-assisted security testing workspace for authorized engagements.
基于 LangChain + LangGraph。Orchestrator(system prompt = mastermind SKILL.md 浓缩)经 delegate_attack / delegate_parallel 调度 5 个攻击 agent;旧 LangGraph 7-node 固定管线保留为 --mode scan 确定性回退。支持混合爬虫、改包重放、跨点价值链、JWT/GraphQL/prototype 检测、Triage 8 检查(含 SRC 合规)、docx/html 报告、Claude-Code 插件模式。