
magika
Fast and accurate AI powered file content types detection

Fast and accurate AI powered file content types detection

Reverse Engineering: Decompiling Binary Code with Large Language Models

MCP-enabled multi-agent framework for declarative YAML-driven agentic workflows, used for AI-assisted code auditing, vulnerability triage, and…

A fast universal code security scanner, written in Rust. Batteries included: supports 14 languages, TUI for triage, secrets, post-quantum audits,…

Static analysis of malicious Python code

LLM-agent-powered concolic execution engine that instruments source code, summarizes path constraints in natural language, and generates test cases…

Plugin for Binary Ninja that integrates local Ollama models to rename functions and variables in decompiled HLIL code, preserving privacy by keeping…

Self-hosted multi-agent environment for Go with LLM-powered pentesting agents (exploiter, reverser, threathunter, webscanner) that automate…

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

AST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…

Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

The code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"

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

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

The Python Code Tutorials

Source code about machine learning and security.

PoC code from DEF CON 25 presentation