
markdown-exfil-tester
Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

Educational Python target range simulating CVE-2026-22807, an AI supply chain RCE via TOCTOU in model loading. Includes vulnerable library, PoC…

Artefacts for blog post on finding CVE-2025-37899 with o3

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

Modern cyber range with 50 hands-on challenges across web, API, cloud, AI, and blue-team security tracks. Features guided attack chains, transparent…

vulnerability in CVE 2025-9998 and solution for those vulnerability with help artificial intelligence

This study analyzes Python pickle deserialization vulnerabilities, focusing on CVE-2024-3568 in Hugging Face Transformers' TFAutoModel. We reproduce…

AI-based malicious code detection and obfuscation system with microservices for detection, packing, and code confusion, plus user and admin services.

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…


Anticipator is an open-source threat detection platform for multi-agent AI systems.

A service to provide protection against prompt injection, jailbreak attacks, and harmful content when interacting with AI services..

AI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.

Technical Details and Exploit for CVE-2024-11394

vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks.

Detailed security advisory for CVE-2025-492025, documenting a UI misrepresentation vulnerability in Copilot AI that injects unintended hyperlinks…

The Security Toolkit for LLM Interactions

Privacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…