#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.
100% Free & Open Source • Privacy-First Security Scanning and AI Code Review CLI

Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate all HTTP requests and responses between…

A secure low code deception runtime framework, leveraging AI for System Virtualization.

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

Proof-of-concept demonstrating prompt injection in Langchain's GraphCypherQAChain leading to SQL injection in Neo4j databases. Includes Docker-based…

Proof-of-concept exploit for CVE-2025-23266 (NVIDIAScape) targeting NVIDIA AI container runtime. Demonstrates container escape via GPU driver…

TP Seguridad Informática UTN FRBA 2021

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

OWASP Web Security Testing Guide RAG system with ChromaDB, MCP for Claude Code

PowerShell-based detection and remediation toolkit for CVE-2025-32711 (EchoLeak), a critical zero-click AI command injection vulnerability in…

Proof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…

This script audits ServiceNow AI Agents for vulnerabilities like CVE-2025-12420, governance gaps, and compliance risks. Powered by CYBERDUDEBIVASH –…

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

A Red Team vs. Blue Team Adversarial AI Simulation.

GitHub Action that scans ML model files for malicious code and security vulnerabilities

Attack surface discovery and AI-assisted triage for security researchers. Endpoint & parameter mapping with actionable testing hints.

rep+ — Burp-style HTTP Repeater for Chrome DevTools with built‑in AI to explain requests and suggest attacks