Security & AI safety

Vulnerability scanning & code security

Vulnerability scanning and code security projects inspect code and infrastructure for security weaknesses, from static analysis of source files to dependency and cloud configuration checks. Some run as coding-agent skills that produce verified, machine-readable findings, as with security-audit-skill, while others scan running systems without installed agents, as Vuls does across Linux, containers, and network devices.

466 agents · most starred first

Top 100 of 466

security-audit-skill★ 76,058

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

prowler★ 15,293

This repo hosts Prowler OSS (CLI and Local Server). Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment for Humans and AI Agents.

codex-security★ 14,211

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

vuls★ 12,358

Agent-less vulnerability scanner for Linux, FreeBSD, Container, WordPress, Programming language libraries, Network devices

deepsec★ 8,453

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

mantis★ 2,814

A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

visa-vulnerability-agentic-harness★ 2,747

Visa Vulnerability Agentic Harness

reagent★ 2,453

Reconstruct and validate C/C++ code from compiled programs with AI.

open-kritt★ 2,435

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

Kunlun-M★ 2,421

KunLun-M — Open-source static code analysis for PHP, Nodejs/JavaScript, Python, Golang, Java and C/C++, with AST-based semantic scanning and one-click AI Agent integration (OpenClaw, Codex, Claude Code, Hermes, and more).

burpgpt★ 2,398

A Burp Suite extension that integrates OpenAI's GPT to perform an additional passive scan for discovering highly bespoke vulnerabilities and enables running traffic-based analysis of any type.

Seep-Reverse-Lab★ 2,258

Agent-Native multi-platform reverse engineering and CWE-602 client-side authorization audit workbench.

Awesome-LLMs-for-Vulnerability-Detection★ 1,597

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.

WPeGPT★ 1,425

An IDA plugin for binary file analysis, powered by AI models such as OpenAI and DeepSeek.

ai-security-tool★ 1,327

🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.

skills★ 1,322

Pashov Audit Group Skills

sast-skills★ 1,286

Collection of agent skills that turn your AI coder into a SAST scanner

AutoCVE★ 1,233

Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

cybergym★ 1,050

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

vigolium★ 1,044

Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision

ReArk★ 985

An intelligent reverse engineering and AI-assisted analysis tool for HarmonyOS NEXT (HAP/APP/ABC), Android (APK/AAB), iOS (IPA), and native PE/ELF/Mach-O binaries.

reaper★ 884

Live validation proxy tool for testing web app vulnerabilities

ship-safe★ 872

The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.

hackerai★ 846

Find and fix vulnerabilities by chatting with AI

vibe-security-skill★ 835

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

VulnHunter★ 825

Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.

GhidrAssist★ 782

An LLM extension for Ghidra to enable AI assistance in RE.

DeepZero★ 779

Find zero-days while you sleep. DeepZero is an automated vulnerability research framework that parses, decompiles, and analyzes thousands of Windows kernel drivers for exploitable IOCTLs natively using AI agents.

FofaMap★ 769

证据驱动的 AI 资产测绘与安全研判工具。以自然语言串联资产发现、AI 反思、授权验证与报告交付,将 FOFA、Nuclei 与 AI 助手融入同一工作流。原生支持 CLI / MCP / Skill / REST API。

GPT_Vuln-analyzer★ 596

Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap scan data, and DNS scan information. It can also perform subdomain enumeration to a great extent

medusa★ 582

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

vice★ 529

VICE is a security auditing CLI tool that finds vulnerabilities in your web applications.

DeepSec★ 518

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

pmg★ 499

PMG protects developers, AI agents from malicious open source packages using proxy, sandbox and SafeDep's threat intelligence feed.

audit★ 498

An 8-stage vulnerability-discovery agent.

hotpatch-for-apache-log4j2★ 496

An agent to hotpatch the log4j RCE from CVE-2021-44228.

agentgg★ 468

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own model.

speca★ 463

SPECA: Specification-to-Checklist Agentic Auditing Framework

RepoAudit★ 461

An autonomous LLM-agent for large-scale, repository-level code auditing

CVEngine★ 451

AI-first external attack surface assessment with continuous discovery, evidence-based vulnerability validation, and developer-agent MCP integration.

skills★ 446

Ghost Security's collection of AppSec skills for AI coding agents

OpenHack★ 445

Open Source Agentic Security Scanner

wxmini-security-audit★ 424

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。

cra-agent★ 394

Autonomous agentic AI for CRA (Cyber Resilience Act) compliance: scans repos, triages findings, opens Jira tickets, and auto-fixes vulnerabilities via PR.

api★ 379

Official Python SDK for the Vulners vulnerability-intelligence API — search CVEs, exploits and advisories (CVSS/EPSS/KEV), audit software, Linux/Windows hosts and SBOMs, and stream the whole graph. Typed sync + async clients, 100% v3-compatible, with a built-in MCP server for AI agents.

BinaryChat★ 375

ChatWithBinary: Advanced AI-powered binary analysis tool leveraging OpenAI & LangChain (2023)

VulnGym★ 371

VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents

skill★ 327

Bộ công cụ và tập hợp skill hỗ trợ phân tích phần mềm, khôi phục cấu trúc nguồn ở mức cần thiết, rà soát bảo mật, kiểm tra phụ thuộc và xây dựng kế hoạch khắc phục cho các hệ thống mà bạn sở hữu hoặc được phép đánh giá.

plamen★ 316

Autonomous Web3 security audit agent for Claude Code

cyber-neo★ 300

Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 categories. 11 security domains, 60+ secret patterns, parallel subagent analysis, professional report generation. Built by tododeia.com

serializationisbad★ 294

A Minecraft coremod / Java Agent aiming to patch serious security vulnerabilities found in many different mods

llm-sast-scanner★ 292

A SAST skill that gives AI coding agents structured vulnerability detection across 34 vulnerability classes.

pya★ 282

PYA (Protect Your Ass): security audit plugin for Claude Code. 9 specialist agents, a dated threat feed, verified findings, offline by default.

open-asm★ 280

Open-source Attack Surface Management. Discover assets. Identify exposure. Own your security data.

binny★ 258

BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

nemesis-auditor★ 252

The Inescapable Auditor -- iterative deep-logic security audit agent for Claude Code

SecOpsAgentKit★ 237

Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan containers, detect secrets, and enforce policies automatically.

claude-cybersecurity★ 225

AI-powered cybersecurity code review skill for Claude Code. 8 specialist agents, OWASP 2025, CWE Top 25, MITRE ATT&CK, 11 languages, zero configuration.

ablation★ 224

Ablation is an AI-assisted reverse engineering (AIARE) framework

lagune★ 222

🪼 Lagune AI is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

ai-reverse-engineering★ 214

AI-Assisted Reverse Engineering with Ghidra

DllMainHijacking★ 208

Resolve the issue of DLLmain function in white and black DLLs hanging when calling shellcode

ESAA-Security★ 202

ESAA-Security applies the ESAA architecture to automated security auditing. LLM-based agents execute a structured audit across 16 security domains, governed by the same immutable append-only event log, boundary contracts, and hash-verified projections that ESAA provides for software engineering workflows. Every finding, classification, and remediat

sec-af★ 200

AI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.

AIxVuln★ 193

一个基于LLM的多Agent全流程漏洞挖掘项目,支持PHP、Java、Python、Go、Node.js等多种语言项目环境搭建、漏洞分析、漏洞验证、报告产出。支持多Agent并发高效率沟通完成漏洞挖掘任务。

SuperGhidra★ 190

SuperGhidra: Autonomous Agent Reverse Engineering, Lock-Free Ghidra Daemon & C++ Recovery Suite

Watchtower★ 187

Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.

openrisk★ 179

openrisk is a tool that generates a risk score based on the results of a Nuclei scan.

awesome-security-vul-llm★ 166

本项目通过大模型联动爬虫,检索Github上所有存有有价值漏洞信息与漏洞POC或规则信息的项目,并自动识别项目的目录结构、Readme信息后进行总结分析并分类,所汇总的项目可以帮助安全行业从业者收集漏洞信息、POC信息、规则等。

wukong-agent★ 160

Web scan foundation framework

AIxVuln_Web★ 147

一个基于LLM的多Agent全流程漏洞挖掘项目,支持PHP、Java、Python、Go、Node.js等多种语言项目环境搭建、漏洞分析、漏洞验证、报告产出。支持多Agent并发高效率完成漏洞挖掘任务,下个版本将会大更新。

AgentRE-Bench★ 145

AgentRE-Bench is an agentic benchmark that evaluates state-of-the-art models on long-horizon reverse engineering tasks, measuring their ability to analyze binaries, use tooling effectively, and reason over multi-step execution artifacts

AI-Surface★ 144

Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS, runs offline.

code-pathfinder★ 143

Static Code Analysis for security teams with Inter file taint analysis. Built for finding vulnerabilities, advanced structural search, derive insights and supports MCP

vibeguard★ 141

Security linter for AI-generated code: catches the exact vulnerabilities Copilot, Cursor and ChatGPT repeatedly produce. SQL injection, hardcoded secrets, JWT bypass, command injection and 15+ more rules. Grade A–F. Zero config. CI/CD ready.

.context★ 121

AI Agent Skills for Security Auditing to generate triaged, industry grade report findings, code locations, pocs, attacker story flow graphs and more

dvalincode★ 118

Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT.

AgentFuzz★ 114

The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents

mcp-observatory★ 114

Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app.

AgentScan★ 110

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。

WPeGPT-Analyzer★ 110

可移植的逆向分析 SKILL 技能,驱动 IDA + WPeGPT 插件,对 PE/ELF 进行三种模式的自动化分析(轻量/全量/漏洞),输出分析报告。支持 SKILL 技能机制的 AI Agent 均可加载使用。

ArgusMind★ 109

AI 驱动的多 Agent 自主代码安全审计:审计计划、危险 Sink 发现与调用链分析;AI-driven multi-agent autonomous code security auditor — audit planning, sink discovery & call-chain analysis;

SEC-bench★ 107

Automated Benchmarking of LLM Agents on Real-World Software Security Tasks [NeurIPS 2025]

AutoFyn★ 102

Run Claude in self-improving loops to optimize measurable goals.

symfony-security-auditor★ 101

AI-powered multi-agent security auditor for Symfony applications, provider-agnostic via symfony/ai.

BinaryAudit★ 100

An open-source benchmark for evaluating AI agents' ability to find backdoors hidden in compiled binaries.

opentaint★ 100

The open source taint analysis tool for the AI era. The analyzer you can customize and self-host, built so AI agents drive your security analysis without burning tokens on every scan. AI-ready open source alternative to Semgrep Pro and CodeQL.

cybergym-e2e★ 100

CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vulnerabilities to generating proof-of-concept to writing patches.

vuln-report-skill★ 99

AI-agent skill: turn confirmed vulnerabilities into submission-ready DOCX reports | 漏洞报告成稿 skill(SRC/0day 提交稿、分层验证门、Step 式 PoC、截图铁律)

piolium★ 98

A Pi-native extension for thorough, agentic security audits

REx-skill★ 98

REx@Skill - Agentic Reverse Engineering eXecution Skill for binary vulnerability discovery

penthera★ 97

Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.

awesome-ai-reverse-engineering★ 97

Open-source AI reverse engineering tools for coding agents: Ghidra MCP, IDA Pro MCP, jadx, Frida, skills and REA. 122 repos, each read and security-graded. EN + 中文.

vulners-agent★ 96

Agent scanner for vulners.com

FirmAgent★ 95

Official repository for the NDSS 2026 research paper titled "FirmAgent: Leveraging Fuzzing to Assist LLM Agents with IoT Firmware Vulnerability Discovery"

seclab-taskflows★ 90

Example taskflows to use with the GitHub Security Lab Taskflow Agent (https://github.com/GitHubSecurityLab/seclab-taskflow-agent)

ultrafuzz★ 89

End-to-end agentic smart contract fuzzing and threat hunting

contrast-rO0★ 88

A tiny Java agent that blocks attacks against unsafe deserialization

malk★ 87

Demonstrate calling a kernel function and handle process creation callback against HVCI

brainblast★ 81

Predict the silent integration traps an AI agent would ship (zero-revenue configs, auth bypasses, immutable wrong choices) — then enforce, in CI, that they stay fixed. Research skill + npx brainblast CLI.

More in Security & AI safety