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

AngularJS 1.x -> Angular 18 migration guidance for GitHub Copilot. Source-of-truth repo for…

Red portatil de reconocimiento inteligente con IA offline

Autonomous AI-powered cyber defense system using MCP, Gemini 2.0 Flash, Dynatrace observability and MongoDB. Google Cloud Hackathon submission.

Security awareness training tool for authorized phishing simulations and internal IT audits

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

Full-stack security OS for AI agents with five-layer defense-in-depth architecture covering foundation scan, input sanitization, cognition…

C++ reimplementation of Ghidra's analytical core without JVM dependencies, providing embeddable binary analysis, Pcode/Sleigh foundations, and…

Benchmark measuring AI models' ability to detect vulnerabilities in source code via real bug bounty cases with balanced recall and false-positive…

Extracted system prompt from Meta's AI Support Assistant on June 1, 2026

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

StealthRL: RL framework for adversarially paraphrasing AI text to stress-test detector robustness.

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo:…

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

Adversary simulation and Red teaming platform with AI

Python library for local LLM-powered security analysis with Ghidra binary analysis, C/C++ vulnerability scanning, and MCP tool integration for…

Automates CAPTCHA solving with multimodal AI models (GPT-4o, Gemini) and Selenium, supporting text, audio, slider puzzles, and reCAPTCHA v2 via a…

Docker Container Escape POC via mlx-metal importlib

Docker Model Runner container-to-host RCE / Escape: A critical vulnerability that allows for container-to-host code execution in the Docker Model…