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

AI-powered cybersecurity chatbot designed to provide helpful and accurate answers to your cybersecurity-related queries and also do code analysis and…

Semantic graph-based version control for AI-written code. Tracks entities and relations instead of file diffs, enabling blast radius analysis, shadow…

Open-source, self-hosted security pipeline for IT, AI and OT. Logs in. Evidence out.: OCSF normalization, 46 detection rules…

Zero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…

Composable research-contract and YAML-recipe framework for agent-operated security experiments on disposable compute

An LLM-driven fuzzing pipeline powered by the GitHub Security Lab Taskflow Agent

Measuring Open Privilege in Agent Defenses

This repository contains the complete record of my three-year research journey, covering the project from foundational concepts to advanced-level…

AI supply-chain BOM: every agent, MCP server and AI package, and what each one can reach. Open-source scanner and self-hosted control plane for code,…

Code, response logs and labels for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations

Runtime Application Self Protection for Python web servers, serverless functions and MCP servers, detecting attacks, prompt injection and data leaks…

Fix-Like Artifacts With Embedded Defects

autonomous red teaming platform; multi-agent offensive-security meta-harness

Security Scanner for Agent Skills

OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery product, helping defenders proactively find verified security flaws…

A monitoring hub that watches popular open-source repositories and uses AI to detect when commits are patching security vulnerabilities - often…

Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.

Research code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…