# Awesome AI Pentesting [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)

> A curated list of AI-powered tools, frameworks, and resources for penetration testing, bug bounty hunting, red teaming, and cybersecurity operations.

The intersection of Artificial Intelligence and offensive/defensive security is evolving rapidly. This list tracks the most impactful open-source projects that leverage LLMs, machine learning, and autonomous agents for cybersecurity.

**Created by [@skyvanguard](https://github.com/skyvanguard)** — Cybersecurity & AI Researcher | TryHackMe Top 1% Global

*Stars updated: July 2026*

---

## Contents

- [Autonomous AI Pentesting Agents](#autonomous-ai-pentesting-agents)
- [MCP Servers for Security](#mcp-servers-for-security)
- [Bug Bounty & Recon AI](#bug-bounty--recon-ai)
- [CTF Solvers & Challenge Tools](#ctf-solvers--challenge-tools)
- [Vulnerability Analysis & Scanning](#vulnerability-analysis--scanning)
- [Red Team & Offensive AI](#red-team--offensive-ai)
- [Blue Team & Defensive AI](#blue-team--defensive-ai)
- [AI Security (Securing AI Systems)](#ai-security-securing-ai-systems)
- [Fuzzing with AI/ML](#fuzzing-with-aiml)
- [Pentest Report Generation](#pentest-report-generation)
- [OSINT with AI](#osint-with-ai)
- [Research Papers & Resources](#research-papers--resources)
- [Contributing](#contributing)

---

## Autonomous AI Pentesting Agents

*Fully autonomous agents that perform end-to-end penetration testing tasks with minimal human intervention.*

| Tool | Description | AI Tool | Stars |
|------|-------------|---------|-------|
| [Shannon](https://github.com/KeygraphHQ/shannon) | Fully autonomous AI hacker using Claude Agent SDK. 96.15% success rate on XBOW Benchmark. Finds and exploits real vulnerabilities in web apps. | Claude API (Agent SDK) | ![Stars](https://img.shields.io/github/stars/KeygraphHQ/shannon?style=flat-square) |
| [Strix](https://github.com/usestrix/strix) | Open-source AI hackers that run code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. | Claude API | ![Stars](https://img.shields.io/github/stars/usestrix/strix?style=flat-square) |
| [PentAGI](https://github.com/vxcontrol/pentagi) | Fully autonomous AI agents system. Docker sandboxed, 20+ built-in tools (nmap, metasploit, sqlmap), Neo4j knowledge graph. | Multi-LLM (OpenAI, Claude, DeepSeek) | ![Stars](https://img.shields.io/github/stars/vxcontrol/pentagi?style=flat-square) |
| [PentestGPT](https://github.com/GreyDGL/PentestGPT) | Automated penetration testing agentic framework powered by LLMs. Published at USENIX Security 2024. | OpenAI API (GPT-4) | ![Stars](https://img.shields.io/github/stars/GreyDGL/PentestGPT?style=flat-square) |
| [CAI](https://github.com/aliasrobotics/cai) | Open-source framework for building AI agents for real-world security testing. Top-10 in Dragos OT CTF 2025. | Multi-LLM (OpenAI, Claude, Ollama/local models) | ![Stars](https://img.shields.io/github/stars/aliasrobotics/cai?style=flat-square) |
| [Decepticon](https://github.com/PurpleAILAB/Decepticon) | Autonomous hacking agent for red teaming. Modular multi-agent architecture built on LangGraph with MCP tool integration. | Multi-LLM (via LiteLLM) | ![Stars](https://img.shields.io/github/stars/PurpleAILAB/Decepticon?style=flat-square) |
| [PentestAgent](https://github.com/GH05TCREW/pentestagent) | AI agent framework for black-box security testing with prebuilt attack playbooks for bug bounty, red-team, and pentest. | OpenAI API (GPT-4) | ![Stars](https://img.shields.io/github/stars/GH05TCREW/pentestagent?style=flat-square) |
| [Pentest-Swarm-AI](https://github.com/Armur-Ai/Pentest-Swarm-AI) | Autonomous pentesting with a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning. Bug bounty, monitoring, and CTF modes. | Claude API | ![Stars](https://img.shields.io/github/stars/Armur-Ai/Pentest-Swarm-AI?style=flat-square) |
| [NeuroSploit](https://github.com/JoasASantos/NeuroSploit) | AI-powered pentest framework with 100 vulnerability types, isolated Kali containers, 9 specialized agent personas. | Multi-LLM (OpenAI, Claude, Ollama/local) | ![Stars](https://img.shields.io/github/stars/JoasASantos/NeuroSploit?style=flat-square) |
| [LuaN1aoAgent](https://github.com/SanMuzZzZz/LuaN1aoAgent) | Cognitive-driven autonomous AI hacker using dual-graph reasoning (causal and attack graphs) for plan-execute-reflect penetration testing. | Multi-LLM (OpenAI, DeepSeek, Claude) | ![Stars](https://img.shields.io/github/stars/SanMuzZzZz/LuaN1aoAgent?style=flat-square) |
| [hackingBuddyGPT](https://github.com/ipa-lab/hackingBuddyGPT) | Academic framework for building LLM-driven ethical hacking agents in ~50 lines of code. Research platform with reproducible privilege-escalation benchmarks. | OpenAI API (GPT-4) | ![Stars](https://img.shields.io/github/stars/ipa-lab/hackingBuddyGPT?style=flat-square) |
| [Pentest Copilot](https://github.com/bugbasesecurity/pentest-copilot) | AI-powered browser-based ethical hacking assistant with agentic architecture that runs commands in the pentest environment. | OpenAI API | ![Stars](https://img.shields.io/github/stars/bugbasesecurity/pentest-copilot?style=flat-square) |
| [Nebula](https://github.com/berylliumsec/nebula) | AI-powered pentesting assistant for automating recon, note-taking, and vulnerability analysis with human decision checkpoints. | OpenAI API (GPT-4) | ![Stars](https://img.shields.io/github/stars/berylliumsec/nebula?style=flat-square) |
| [Darkmoon](https://github.com/ASCIT31/Dark-Moon) | Open source autonomous AI penetration testing platform that orchestrates 80+ offensive tools through Markdown playbooks and MCP controlled execution, covering web, cloud, Active Directory, Kubernetes and API with an evidence trail per finding. | Multi-LLM (OpenAI, Anthropic, Ollama/local) | ![Stars](https://img.shields.io/github/stars/ASCIT31/Dark-Moon?style=flat-square) |
| [ARTEMIS](https://github.com/Stanford-Trinity/ARTEMIS) | ARTEMIS is an autonomous agent created by the Stanford Trinity project to automate vulnerability discovery. | OpenAI API (GPT-4) | ![Stars](https://img.shields.io/github/stars/Stanford-Trinity/ARTEMIS?style=flat-square) |
| [AIDA](https://github.com/Vasco0x4/AIDA) | AI-Driven Security Assessment that connects AI to 400+ pentesting tools via MCP (Exegol container), enabling natural language-driven security workflows. | Multi-LLM (OpenAI, Claude, Ollama via MCP) | ![Stars](https://img.shields.io/github/stars/Vasco0x4/AIDA?style=flat-square) |
| [BugTraceAI](https://github.com/BugTraceAI/BugTraceAI) | Open-source multi-agent platform for authorized web application security testing with validation, evidence capture, and reporting. | Multi-LLM | ![Stars](https://img.shields.io/github/stars/BugTraceAI/BugTraceAI?style=flat-square) |

## MCP Servers for Security

*Model Context Protocol servers that bridge AI assistants with cybersecurity tools.*

| Tool | Description | Stars |
|------|-------------|-------|
| [HexStrike AI](https://github.com/0x4m4/hexstrike-ai) | Advanced MCP server with 150+ cybersecurity tools. Lets AI agents autonomously run pentesting, vuln discovery, and bug bounty tools. | ![Stars](https://img.shields.io/github/stars/0x4m4/hexstrike-ai?style=flat-square) |
| [MCP-Security-Checklist](https://github.com/slowmist/MCP-Security-Checklist) | Comprehensive security checklist for MCP-based AI tools by SlowMist. Input validation, audit capability, and risk assessment. | ![Stars](https://img.shields.io/github/stars/slowmist/MCP-Security-Checklist?style=flat-square) |
| [mcp-security-hub](https://github.com/FuzzingLabs/mcp-security-hub) | 36 MCP servers with 175+ tools: Nmap, Ghidra, Nuclei, SQLMap, Hashcat. Recon, web sec, binary analysis, blockchain, AD. | ![Stars](https://img.shields.io/github/stars/FuzzingLabs/mcp-security-hub?style=flat-square) |
| [awesome-mcp-security](https://github.com/Puliczek/awesome-mcp-security) | Curated collection of MCP security resources: tools, papers, videos, articles, and vulnerability information. | ![Stars](https://img.shields.io/github/stars/Puliczek/awesome-mcp-security?style=flat-square) |
| [mcp-for-security](https://github.com/cyproxio/mcp-for-security) | MCP server implementations for SQLMap, FFUF, NMAP, Masscan and more security testing tools. | ![Stars](https://img.shields.io/github/stars/cyproxio/mcp-for-security?style=flat-square) |
| [awesome-cyber-security-mcp](https://github.com/MorDavid/awesome-cyber-security-mcp) | Curated list of MCP servers focused on cybersecurity operations. | ![Stars](https://img.shields.io/github/stars/MorDavid/awesome-cyber-security-mcp?style=flat-square) |
| [pentestMCP](https://github.com/ramkansal/pentestMCP) | AI-powered penetration testing via MCP. 20+ security assessment tools (Nmap, Nuclei, ZAP, SQLMap) through MCP protocol. | ![Stars](https://img.shields.io/github/stars/ramkansal/pentestMCP?style=flat-square) |
| [mcp-server-security-standard](https://github.com/mcp-security-standard/mcp-server-security-standard) | Open, testable security control standard (MSSS) for certifying MCP servers with levels and evidence requirements. | ![Stars](https://img.shields.io/github/stars/mcp-security-standard/mcp-server-security-standard?style=flat-square) |
| [PentestThinkingMCP](https://github.com/ibrahimsaleem/PentestThinkingMCP) | AI pentesting reasoning engine with Beam Search, MCTS, attack scoring for attack path planning and CTF solving. | ![Stars](https://img.shields.io/github/stars/ibrahimsaleem/PentestThinkingMCP?style=flat-square) |
| [mcp-vanguard](https://github.com/skyvanguard/mcp-vanguard) | Security pentesting MCP Server with 22 tools. Windows/WSL bridge for Kali tools integration with Claude. | ![Stars](https://img.shields.io/github/stars/skyvanguard/mcp-vanguard?style=flat-square) |
| [DomScan](https://github.com/estevecastells/domscan-mcp) | Hosted domain intelligence MCP for DNS, WHOIS/RDAP, TLS, subdomains, reputation, email security, and typosquatting. | ![Stars](https://img.shields.io/github/stars/estevecastells/domscan-mcp?style=flat-square) |

## Bug Bounty & Recon AI

*AI-enhanced tools for reconnaissance and bug bounty automation.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Nuclei](https://github.com/projectdiscovery/nuclei) | Fast vulnerability scanner with YAML-based DSL. AI-powered template generation via `-ai` flag. 10k+ community templates. | ![Stars](https://img.shields.io/github/stars/projectdiscovery/nuclei?style=flat-square) |
| [Sn1per](https://github.com/1N3/Sn1per) | Attack surface management platform combining automated scanning with intelligent analysis. | ![Stars](https://img.shields.io/github/stars/1N3/Sn1per?style=flat-square) |
| [awesome-bugbounty-tools](https://github.com/vavkamil/awesome-bugbounty-tools) | Curated list of bug bounty tools including AI-enhanced scanners and recon automation frameworks. | ![Stars](https://img.shields.io/github/stars/vavkamil/awesome-bugbounty-tools?style=flat-square) |
| [AutoSploit](https://github.com/NullArray/AutoSploit) | Automated mass exploiter combining Shodan/Censys/Zoomeye for target discovery with Metasploit for exploitation. | ![Stars](https://img.shields.io/github/stars/NullArray/AutoSploit?style=flat-square) |
| [BigBountyRecon](https://github.com/Viralmaniar/BigBountyRecon) | 58 different techniques using Google dorks and open source tools for initial reconnaissance. | ![Stars](https://img.shields.io/github/stars/Viralmaniar/BigBountyRecon?style=flat-square) |
| [Mantis](https://github.com/PhonePe/mantis) | Security framework automating discovery, reconnaissance, and vulnerability scanning. Chains multiple tools from domain input. | ![Stars](https://img.shields.io/github/stars/PhonePe/mantis?style=flat-square) |
| [ReconAIzer](https://github.com/hisxo/ReconAIzer) | Burp Suite extension using OpenAI GPT to discover endpoints, params, URLs, and subdomains during bug bounty recon. | ![Stars](https://img.shields.io/github/stars/hisxo/ReconAIzer?style=flat-square) |
| [HackBot](https://github.com/morpheuslord/HackBot) | AI-powered cybersecurity chatbot using LLaMA for code analysis, scan analysis, and cybersecurity Q&A. | ![Stars](https://img.shields.io/github/stars/morpheuslord/HackBot?style=flat-square) |

## CTF Solvers & Challenge Tools

*AI tools for solving Capture The Flag competitions and security challenges.*

| Tool | Description | Stars |
|------|-------------|-------|
| [AI-Goat](https://github.com/dhammon/ai-goat) | Learn AI security through vulnerable LLM CTF challenges. Run locally, no sign-ups or cloud fees needed. | ![Stars](https://img.shields.io/github/stars/dhammon/ai-goat?style=flat-square) |
| [ChatGPT on CTF](https://github.com/LiuYuancheng/ChatGPT_on_CTF) | Research testing whether AI-LLMs can solve CTF challenges by running commands in test environments. | ![Stars](https://img.shields.io/github/stars/LiuYuancheng/ChatGPT_on_CTF?style=flat-square) |
| [LLM-Security-CTF](https://github.com/TrustAI-laboratory/LLM-Security-CTF) | Learn LLM/AI security through CTF challenges: prompt injection, jailbreaks, guardrail bypass, tool abuse. | ![Stars](https://img.shields.io/github/stars/TrustAI-laboratory/LLM-Security-CTF?style=flat-square) |
| [EnIGMA](https://arxiv.org/abs/2409.16165) | Enhanced Interactive Generative Model Agent. State-of-the-art on NYU CTF and CyBench. 3x more challenges than prior agents. (ICML 2025) | Paper |
| [CTFAgent](https://www.sciencedirect.com/science/article/abs/pii/S2214212625003424) | LLM-powered CTF solver with plan-and-execute paradigm. Outperforms 88% of human CTF participants. | Paper |
| [CSAW Agentic CTF](https://www.csaw.io/agentic-automated-ctf) | CSAW competition using generative autonomous AI to solve CTF challenges. Major academic AI security benchmark. | Competition |

## Vulnerability Analysis & Scanning

*AI-powered vulnerability discovery and code analysis tools.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Semgrep](https://github.com/semgrep/semgrep) | Lightweight static analysis for finding bugs and enforcing code standards with AI pattern matching. | ![Stars](https://img.shields.io/github/stars/semgrep/semgrep?style=flat-square) |
| [Garak](https://github.com/NVIDIA/garak) | NVIDIA's LLM vulnerability scanner. Probes for hallucination, data leakage, prompt injection, toxicity, and jailbreaks. | ![Stars](https://img.shields.io/github/stars/NVIDIA/garak?style=flat-square) |
| [agent-scan](https://github.com/snyk/agent-scan) | Snyk's security scanner for AI agents, MCP servers and agent skills. Detects prompt injections and tool poisoning. | ![Stars](https://img.shields.io/github/stars/snyk/agent-scan?style=flat-square) |
| [Vulnhuntr](https://github.com/protectai/vulnhuntr) | Zero-shot vulnerability discovery using Claude AI. Analyzes Python call chains. Found 12+ zero-days in production code. | ![Stars](https://img.shields.io/github/stars/protectai/vulnhuntr?style=flat-square) |
| [Agentic Security](https://github.com/msoedov/agentic_security) | LLM vulnerability scanner / AI red teaming kit. Protects AI systems from jailbreaks, fuzzing, and multimodal attacks. | ![Stars](https://img.shields.io/github/stars/msoedov/agentic_security?style=flat-square) |
| [Agentic Radar](https://github.com/splx-ai/agentic-radar) | Security scanner for agentic systems. Workflow visualization, tool identification, MCP server detection, vulnerability mapping. | ![Stars](https://img.shields.io/github/stars/splx-ai/agentic-radar?style=flat-square) |
| [ModelScan](https://github.com/protectai/modelscan) | Scans ML models for unsafe code. Supports H5, Pickle, SavedModel, and more formats. | ![Stars](https://img.shields.io/github/stars/protectai/modelscan?style=flat-square) |
| [NVIDIA Vulnerability Analysis](https://github.com/NVIDIA-AI-Blueprints/vulnerability-analysis) | NVIDIA blueprint for identifying and mitigating container security vulnerabilities with generative AI. | ![Stars](https://img.shields.io/github/stars/NVIDIA-AI-Blueprints/vulnerability-analysis?style=flat-square) |

## Red Team & Offensive AI

*Offensive AI tools, adversarial ML, and AI red teaming frameworks.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Promptfoo](https://github.com/promptfoo/promptfoo) | LLM red teaming, pentesting, and vuln scanning with 100+ attack types. Tests complete AI systems including RAG and agents. | ![Stars](https://img.shields.io/github/stars/promptfoo/promptfoo?style=flat-square) |
| [Social-Engineer-Toolkit](https://github.com/trustedsec/social-engineer-toolkit) | Open-source penetration testing framework designed for social engineering. | ![Stars](https://img.shields.io/github/stars/trustedsec/social-engineer-toolkit?style=flat-square) |
| [Caldera](https://github.com/apache/caldera) | Automated adversary emulation platform with AI-driven attack planning. Originally by MITRE, now an Apache project. | ![Stars](https://img.shields.io/github/stars/apache/caldera?style=flat-square) |
| [Adversarial Robustness Toolbox](https://github.com/Trusted-AI/adversarial-robustness-toolbox) | IBM's Python library for ML Security: evasion, poisoning, extraction, inference attacks and defenses. | ![Stars](https://img.shields.io/github/stars/Trusted-AI/adversarial-robustness-toolbox?style=flat-square) |
| [llm-attacks](https://github.com/llm-attacks/llm-attacks) | Universal and transferable attacks on aligned language models. Academic research on adversarial attacks against LLMs. | ![Stars](https://img.shields.io/github/stars/llm-attacks/llm-attacks?style=flat-square) |
| [DeepTeam](https://github.com/confident-ai/deepteam) | Framework for red teaming LLMs. 10+ adversarial attacks, supports OWASP Top 10 for LLMs and NIST AI RMF. | ![Stars](https://img.shields.io/github/stars/confident-ai/deepteam?style=flat-square) |
| [ai-exploits](https://github.com/protectai/ai-exploits) | Collection of real-world AI/ML exploits for responsibly disclosed vulnerabilities. | ![Stars](https://img.shields.io/github/stars/protectai/ai-exploits?style=flat-square) |
| [offensive-ai-compilation](https://github.com/jiep/offensive-ai-compilation) | Curated list of Offensive AI resources: tools, techniques, research papers, and attack methodologies. | ![Stars](https://img.shields.io/github/stars/jiep/offensive-ai-compilation?style=flat-square) |
| [PyRIT](https://github.com/Azure/PyRIT) | Microsoft's Python Risk Identification Tool for red teaming generative AI systems. | ![Stars](https://img.shields.io/github/stars/Azure/PyRIT?style=flat-square) |

## Blue Team & Defensive AI

*AI tools for defense, detection, and incident response.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Wazuh](https://github.com/wazuh/wazuh) | Open-source security monitoring with AI-enhanced threat detection, SIEM, and XDR. | ![Stars](https://img.shields.io/github/stars/wazuh/wazuh?style=flat-square) |
| [Sigma](https://github.com/SigmaHQ/sigma) | Generic signature format for SIEM systems with AI-powered rule creation. | ![Stars](https://img.shields.io/github/stars/SigmaHQ/sigma?style=flat-square) |
| [Falco](https://github.com/falcosecurity/falco) | Cloud Native Runtime Security by CNCF. Detects threats across containers, hosts, K8s, and cloud. | ![Stars](https://img.shields.io/github/stars/falcosecurity/falco?style=flat-square) |
| [Guardrails AI](https://github.com/guardrails-ai/guardrails) | Adding guardrails to LLMs. Input/output validation, content moderation, and PII detection. | ![Stars](https://img.shields.io/github/stars/guardrails-ai/guardrails?style=flat-square) |
| [NeMo Guardrails](https://github.com/NVIDIA-NeMo/Guardrails) | NVIDIA's toolkit for programmable guardrails on LLM systems. Content moderation, jailbreak detection. | ![Stars](https://img.shields.io/github/stars/NVIDIA-NeMo/Guardrails?style=flat-square) |
| [LLM Guard](https://github.com/protectai/llm-guard) | Security toolkit for LLM interactions. Scanners for PII, prompt injection, banned topics, data leakage. | ![Stars](https://img.shields.io/github/stars/protectai/llm-guard?style=flat-square) |
| [Redcells](https://redcells.net) | Automated adversarial testing platform for LLMs you own or control. Runs structured red-team jobs (prompt injection, jailbreak, data leakage, etc.) with iterative attack→refine layers and per-layer judge scoring via web dashboard or API. | [Repo](https://github.com/awdemos/redcell) |
| [Shuffle](https://github.com/Shuffle/Shuffle) | Open-source SOAR platform for security automation and orchestration. | ![Stars](https://img.shields.io/github/stars/Shuffle/Shuffle?style=flat-square) |
| [GhostWriter](https://github.com/GhostManager/Ghostwriter) | Report management platform for red/blue team operations with AI-assisted analysis. | ![Stars](https://img.shields.io/github/stars/GhostManager/Ghostwriter?style=flat-square) |

## AI Security (Securing AI Systems)

*Tools for defending AI/LLM systems against prompt injection, jailbreaks, and emerging threats.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Rebuff](https://github.com/protectai/rebuff) | LLM prompt injection detector. Multi-layered defense: heuristics, LLM-based detection, vector DB, canary tokens. | ![Stars](https://img.shields.io/github/stars/protectai/rebuff?style=flat-square) |
| [awesome-mcp-security](https://github.com/Puliczek/awesome-mcp-security) | Collection of MCP security resources: vulnerabilities, tools, papers, and mitigation strategies. | ![Stars](https://img.shields.io/github/stars/Puliczek/awesome-mcp-security?style=flat-square) |
| [prompt-injection-defenses](https://github.com/tldrsec/prompt-injection-defenses) | Every practical and proposed defense against prompt injection attacks. Comprehensive reference. | ![Stars](https://img.shields.io/github/stars/tldrsec/prompt-injection-defenses?style=flat-square) |
| [Awesome-LLMSecOps](https://github.com/wearetyomsmnv/Awesome-LLMSecOps) | LLM Security Operations in one repo. Curated links covering the full LLMSecOps lifecycle. | ![Stars](https://img.shields.io/github/stars/wearetyomsmnv/Awesome-LLMSecOps?style=flat-square) |
| [parry-guard](https://github.com/vaporif/parry-guard) | Prompt injection scanner for AI coding tools (Claude Code, Codex). Runs DeBERTa/Llama transformers locally in Rust via Candle or ONNX. | ![Stars](https://img.shields.io/github/stars/vaporif/parry-guard?style=flat-square) |

## Fuzzing with AI/ML

*Machine learning-guided fuzzing and automated test generation tools.*

| Tool | Description | Stars |
|------|-------------|-------|
| [AFL++](https://github.com/AFLplusplus/AFLplusplus) | Superior fork of AFL with ML-guided mutation strategies. Industry standard for fuzzing. | ![Stars](https://img.shields.io/github/stars/AFLplusplus/AFLplusplus?style=flat-square) |
| [FuzzyAI](https://github.com/cyberark/FuzzyAI) | CyberArk's automated LLM fuzzing tool for finding jailbreaks and security vulnerabilities in LLM APIs. | ![Stars](https://img.shields.io/github/stars/cyberark/FuzzyAI?style=flat-square) |
| [OSS-Fuzz-Gen](https://github.com/google/oss-fuzz-gen) | Google's LLM-powered fuzzing via OSS-Fuzz. Generates fuzz targets for C/C++. 29% max line coverage increase. | ![Stars](https://img.shields.io/github/stars/google/oss-fuzz-gen?style=flat-square) |
| [SecPipe](https://github.com/FuzzingLabs/secpipe) | MCP server for AI-driven security pipelines. Workflow automation for AppSec and fuzzing with intelligent agents. Formerly FuzzForge AI. | ![Stars](https://img.shields.io/github/stars/FuzzingLabs/secpipe?style=flat-square) |
| [EvoMaster](https://github.com/WebFuzzing/EvoMaster) | First open-source AI-driven tool for system-level test generation. Evolutionary algorithms for REST, GraphQL, RPC. | ![Stars](https://img.shields.io/github/stars/WebFuzzing/EvoMaster?style=flat-square) |
| [ToolFuzz](https://github.com/eth-sri/ToolFuzz) | First framework for testing LLM agent tools. Combines fuzzing with LLMs for correctness evaluation. | ![Stars](https://img.shields.io/github/stars/eth-sri/ToolFuzz?style=flat-square) |

## Pentest Report Generation

*AI tools for automated penetration testing report creation.*

| Tool | Description | Stars |
|------|-------------|-------|
| [PwnDoc](https://github.com/pwndoc/pwndoc) | Pentest report generator for findings and customizable Docx reports with templates. | ![Stars](https://img.shields.io/github/stars/pwndoc/pwndoc?style=flat-square) |
| [SysReptor](https://github.com/Syslifters/sysreptor) | Customizable pentest reporting platform with AI-assisted writing and finding descriptions. | ![Stars](https://img.shields.io/github/stars/Syslifters/sysreptor?style=flat-square) |
| [APTRS](https://github.com/APTRS/APTRS) | Automated Pentest Reporting System. Python/Django-based. PDF/Excel generation, project tracking. | ![Stars](https://img.shields.io/github/stars/APTRS/APTRS?style=flat-square) |
| [Faction](https://github.com/factionsecurity/faction) | Pen test report generation and assessment collaboration platform. | ![Stars](https://img.shields.io/github/stars/factionsecurity/faction?style=flat-square) |

## OSINT with AI

*AI-powered Open Source Intelligence tools.*

| Tool | Description | Stars |
|------|-------------|-------|
| [Sherlock](https://github.com/sherlock-project/sherlock) | Hunt down social media accounts by username across 400+ social networks. | ![Stars](https://img.shields.io/github/stars/sherlock-project/sherlock?style=flat-square) |
| [SpiderFoot](https://github.com/smicallef/spiderfoot) | Automated OSINT platform. 200+ data sources, threat surface mapping, most modules need no API keys. | ![Stars](https://img.shields.io/github/stars/smicallef/spiderfoot?style=flat-square) |
| [GHunt](https://github.com/mxrch/GHunt) | Offensive Google framework for OSINT. | ![Stars](https://img.shields.io/github/stars/mxrch/GHunt?style=flat-square) |
| [theHarvester](https://github.com/laramies/theHarvester) | E-mails, subdomains and names harvester for OSINT. | ![Stars](https://img.shields.io/github/stars/laramies/theHarvester?style=flat-square) |
| [Recon-ng](https://github.com/lanmaster53/recon-ng) | Full-featured web reconnaissance framework with modular design. | ![Stars](https://img.shields.io/github/stars/lanmaster53/recon-ng?style=flat-square) |
| [Taranis AI](https://github.com/taranis-ai/taranis-ai) | Advanced OSINT tool using NLP-powered news collection and AI for situational analysis. | ![Stars](https://img.shields.io/github/stars/taranis-ai/taranis-ai?style=flat-square) |
| [OSINTGPT](https://github.com/estebanpdl/osintgpt) | OSINT analysis tool leveraging GPT embeddings and vector search for document similarity. | ![Stars](https://img.shields.io/github/stars/estebanpdl/osintgpt?style=flat-square) |

## Research Papers & Resources

### Papers
- [PentestGPT: An LLM-empowered Automatic Penetration Testing Tool](https://arxiv.org/abs/2308.06782) — USENIX Security 2024
- [LLM Agents can Autonomously Hack Websites](https://arxiv.org/abs/2402.06664) — GPT-4 hacks 73% of test websites
- [Getting pwn'd by AI: Penetration Testing with LLMs](https://arxiv.org/abs/2308.00121) — Systematic study
- [AutoAttacker: LLM Guided Automatic Cyber-attacks](https://arxiv.org/abs/2403.01038) — Autonomous attack systems
- [EnIGMA: Enhanced Interactive Generative Model Agent for CTF](https://arxiv.org/abs/2409.16165) — ICML 2025

### Awesome Lists
| List | Description | Stars |
|------|-------------|-------|
| [awesome-pentest](https://github.com/enaqx/awesome-pentest) | General pentesting resources. | ![Stars](https://img.shields.io/github/stars/enaqx/awesome-pentest?style=flat-square) |
| [Awesome-GPT-Agents](https://github.com/fr0gger/Awesome-GPT-Agents) | GPT agents for cybersecurity: offensive, defensive, and analytical. | ![Stars](https://img.shields.io/github/stars/fr0gger/Awesome-GPT-Agents?style=flat-square) |
| [Awesome-LLM4Cybersecurity](https://github.com/tmylla/Awesome-LLM4Cybersecurity) | LLMs for cybersecurity: pentesting reasoning, exploit generation, vulnerability detection. | ![Stars](https://img.shields.io/github/stars/tmylla/Awesome-LLM4Cybersecurity?style=flat-square) |
| [awesome-llm-security](https://github.com/corca-ai/awesome-llm-security) | Tools, documents, and projects about LLM Security. | ![Stars](https://img.shields.io/github/stars/corca-ai/awesome-llm-security?style=flat-square) |
| [awesome-cybersecurity-agentic-ai](https://github.com/raphabot/awesome-cybersecurity-agentic-ai) | Autonomous security agents, frameworks, and research. | ![Stars](https://img.shields.io/github/stars/raphabot/awesome-cybersecurity-agentic-ai?style=flat-square) |
| [awesome-skills-security](https://github.com/Eyadkelleh/awesome-skills-security) | Curated skill set of security-focused Claude Code skills. | ![Stars](https://img.shields.io/github/stars/Eyadkelleh/awesome-skills-security?style=flat-square) |
| [awesome-ai-cybersecurity](https://github.com/ElNiak/awesome-ai-cybersecurity) | Resources for AI in cybersecurity. Collection for professionals and researchers. | ![Stars](https://img.shields.io/github/stars/ElNiak/awesome-ai-cybersecurity?style=flat-square) |

### Standards & Frameworks
- [OWASP AI Security and Privacy Guide](https://owasp.org/www-project-ai-security-and-privacy-guide/)
- [MITRE ATLAS](https://atlas.mitre.org/) — Adversarial Threat Landscape for AI Systems
- [NIST AI Risk Management Framework](https://www.nist.gov/artificial-intelligence)

---

## Contributing

Contributions welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md) before submitting a PR.

### Criteria for Inclusion
- Open-source with a GitHub repository
- Uses AI/ML in a meaningful way for security
- Actively maintained (commits within 12 months)
- Has documentation

---

## Disclaimer

Tools listed are for **educational purposes and authorized security testing only**. Always obtain proper authorization before testing systems you do not own. The maintainers are not responsible for misuse.

---

<p align="center">
  <i>Created by <a href="https://github.com/skyvanguard">@skyvanguard</a></i><br>
  <sub>If this list helped you, consider giving it a star!</sub>
</p>