Official repo for paper "Khaos: The Impact of Inter-procedural Code Obfuscation on Binary Diffing Techniques".

[IJCAI'25] BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Models

MBA deobfuscator via Program Synthesis and Term Rewriting

Mixed Boolean-Arithmetic

Plan and autonomously build a software task end-to-end. One ready-to-paste /goal, adaptive phase count, memory preload + writeback, 3-strike self-healing recovery. Works on Claude Code and Codex.

The windbg skill gives AI the ability to execute WinDbg commands. Typical use cases include kernel debugging, user-mode process debugging, and crash dump analysis.

WinDbg Copilot - Agentic Debugging extension

Imports Reconstructor

Jailbreak for A8 through A11, T2 devices, on iOS/iPadOS/tvOS 15.0, bridgeOS 5.0 and higher.

Hardening code obfuscation against automated attacks

Yet another llvm based obfuscator based on goron.

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

Polaris: An LLVM-based obfuscator that protects software at various levels

Reverse engineering skills for Claude Code | 逆向工程 Claude Code Skills 插件

An LLVM-based obfuscation tool designed to confuse LLM clients interacting with custom MCP disassembler servers.

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

[SCIS 2025] A Survey on Large Language Models for Software Engineering

Anti-LLM obfuscation via finger counting

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

Skills for Real Engineers. Straight from my .claude directory.

《动手学大模型Dive into LLMs》系列编程实践教程

Cloak, Honey, Trap: Proactive Defenses Against LLM Agents

Windows Analysis and Research Toolkit

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

使用skill让 AI Agent 像安全分析师一样分析恶意样本 | AI Agent skill for automated malware analysis using IDA Pro