A global community of security researchers, developers, and enthusiasts building open-source tools to secure generative AI applications and infrastructure.
GenSecAI is a non-profit community dedicated to using generative AI to defend against AI-powered attacks. We build open-source tools to secure our digital future from emerging AI threats, making AI security accessible to everyone.
Detect npm packages compromised in the Shai-Hulud 2.0 supply-chain attack with a battle-tested GitHub Action and CLI.
- Features: Lockfile and repo scanning, SARIF reports, CI/CD integration, allowlist support
- Tech Stack: TypeScript, GitHub Actions, Node.js
- Target: Supply chain security for npm projects
Security scanner for CVE-2025-55182 – a critical RCE vulnerability in React Server Components.
- Features: Scans npm/pnpm/yarn lockfiles, Docker images, SBOMs, and live URLs; auto-fix mode; SARIF output; GitHub Actions; Vercel runtime protection middleware
- Tech Stack: TypeScript, Node.js, GitHub Actions
- Use Case: React2Shell exposure detection and mitigation
AI-powered security operations with Wazuh SIEM + Claude Desktop.
Transform your SOC with natural language threat detection, automated incident response & compliance monitoring.
- Features: Real-time monitoring, ML anomaly detection, conversational security analysis
- Tech Stack: Python, Wazuh, MCP Protocol
- Status: Production-ready
Developer-first Kubernetes security scanner with instant pod replay.
Debug production issues locally in seconds with AI-powered explanations.
- Features: CERT-IN friendly posture, instant pod replay, AI-guided diagnostics
- Tech Stack: Go, Kubernetes, AI/ML
- Use Case: Kubernetes security scanning and compliance
“The Trivy of MCP security” – a Security Command Center for Model Context Protocol (MCP) servers.
- Features: Detects prompt injection, tool poisoning, secret exposure, and misconfigurations; OWASP MCP Top 10 coverage; SARIF/JSON/HTML/PDF outputs
- Tech Stack: Python, FastAPI, MCP client + YARA rules
- Use Case: Continuous security scanning of MCP servers and CI/CD pipelines
Manage pfSense firewalls using natural language through AI assistants like Claude Desktop.
- Features: 5-level RBAC, REST/XML-RPC/SSH support, built-in compliance checks
- Tech Stack: Python, pfSense, MCP Protocol
- Benefits: Natural language firewall management
API security testing tool that leverages multiple Large Language Models (LLMs) to perform intelligent, context-aware API security assessments.
- Features: Multi-LLM support, context-aware testing, automated vulnerability discovery
- Tech Stack: Python, multiple LLM providers
- Target: API security testing
Automates the scanning process using OpenSCAP Security Guide to harden Ubuntu systems, aligning with DISA-STIG-style compliance.
- Features: Ubuntu 24.04 LTS minimum, opinionated hardening, compliance-friendly profiles
- Tech Stack: Shell scripting, OpenSCAP
- Purpose: System hardening and compliance
Modern web application utilizing Next.js App Router to perform robust RDAP queries.
- Features: Domain/IP/ASN/entity lookup, modern UI, security-centric checks
- Tech Stack: TypeScript/JavaScript, Next.js
- Benefits: Structured registration & domain intelligence data
Demonstrates various MCP poisoning attacks affecting real-world AI agent workflows.
- Purpose: Security research and awareness
- Target: AI agent and tool security
- Type: Proof of Concept
Shell scripts to identify and remediate installations of xz-utils affected by CVE-2024-3094.
- Features: Detection, downgrade/rollback options, Ansible playbook
- Use Case: Fleet-wide validation during critical backdoor incidents
A comprehensive MCP server for analyzing SonicWall firewall logs from SonicOS 7.x and 8.x.
- Features: Intelligent log analysis, threat detection, security insights via MCP tools
- Tech Stack: TypeScript, MCP, SSE/HTTP transport
- Compatibility: SonicOS 7.x and 8.x
A meticulously crafted collection of 75+ specialized Claude Code sub-agents for comprehensive software development support.
- Features: Curated sub-agents, accuracy-focused, efficiency-optimized
- Tech Stack: Claude Code framework
- Purpose: Enhanced AI-assisted development
Specialized framework for MCP development featuring 8 Claude Code sub-agents and production-ready templates.
- Features: Security hooks, FastMCP server templates, markdown-driven agents
- Tech Stack: Python, FastMCP, MCP Protocol
- Benefits: Immediate MCP development assistance
Simplifies obtaining and managing Let’s Encrypt IP certificates with automatic renewal and comprehensive validation.
- Features: Automatic renewal, robust validation, logging
- Tech Stack: Shell scripting, Let’s Encrypt/Certbot
- Use Case: SSL certificate management for IP-only endpoints
Simple shell script for automating the installation and renewal of Let’s Encrypt SSL certificates on Linux servers using Nginx.
- Features: Automated installation, renewal, Nginx integration
- Tech Stack: Shell scripting, Nginx, Let’s Encrypt
- Purpose: Simplify SSL certificate management
We believe in the power of community-driven security research.
Our projects are:
- ✅ 100% Open Source – All tools are freely available
- 🌍 Globally Collaborative – Contributors from around the world
- 🧪 Research-Focused – Advancing the state of AI and security
- 🧱 Practical & Production-Ready – Real-world, deployable solutions
- Browse our repositories for tools that match your needs
- Check individual project documentation for installation and deployment guides
- Join our community discussions to share insights and get help
- Fork the repository you’re interested in
- Create a feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
- 15+ Active Projects – Covering multiple areas of AI and security
- Growing Community – Security researchers, developers, and enthusiasts
- Global Reach – Contributors and users worldwide
- Enterprise-Ready – Tools used in production environments
- Website: gensecai.org
- Email: [email protected]
- Twitter: @GensecAI
- GitHub: github.com/gensecaihq
- AI-First Security – We leverage AI to defend against AI threats
- Open Source Philosophy – Democratizing AI security for everyone
- Practical Solutions – Production-ready tools, not just research
- Community Driven – Built by the community, for the community
- Compliance Focus – Tools designed with regulatory requirements in mind
Most of our projects are released under open-source licenses (MIT, Apache 2.0, etc.).
Please check individual repositories for specific licensing information.
As a non-profit organization, we rely on community support to continue our work. You can help by:
- ⭐ Starring our repositories
- 🐛 Reporting bugs and suggesting features
- 🧩 Contributing code and documentation
- 📣 Spreading the word about our projects
- ☁️ Supporting our infrastructure costs
Building a secure AI future, one commit at a time.
Made with ❤️ by the GenSecAI Community