


Hands-on AI security lab platform with 50+ scenarios across prompt injection, agentic system exploitation, model manipulation, and MCP trust boundary…



A practical framework identifying and prioritizing the top security risks in AI datacenter infrastructure, covering hardware, networking, management…

A curated library of security prompts for AI-assisted security testing, threat modeling, and educational exercises.

Structured evaluation criteria framework for assessing Web Application Firewalls (WAFs), enabling users, vendors, and third parties to compare…

Security standard for agent skills, providing guidelines and best practices to secure AI-driven autonomous agents in cloud and API environments.

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

Lightweight Python-based IDS that monitors network traffic in real-time using Scapy, detecting DoS/DDoS attacks via per-IP request rate analysis with…

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

Open-source web application security challenge platform with auto-approved registration, SQL dump generation, and Docker deployment for hands-on…

This project is about creating and publishing threat model examples.

Go-based Web Application Firewall library compatible with ModSecurity SecLang rules and OWASP Core Rule Set v4, providing real-time HTTP traffic…

Full VAPT writeup of OWASP CICD-Goat — 9 CTFd flags captured, 4 critical + 5 high findings (incl. CVE-2024-23897) mapped to the OWASP Top 10 CI/CD…

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP

Atomic web vulnerability labs. One OWASP flaw per app — minimal Flask + Docker, intentionally broken for hands-on study with Burp Suite.

Curated list of web application security resources including books, tools, cheat sheets, labs, and courses for learning penetration testing and…