
FuzzingBrain-Bench
A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

A benchmark for LLM-driven bug discovery: 77 challenges across 43 open-source projects (C/C++/Java).

MCP server bridging Ghidra's reverse engineering with AI tools: 256 tools for decompilation, P-code emulation, live debugging, data flow analysis,…


End-to-end agentic smart contract fuzzing and threat hunting

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

AI harness for long-running code audits, web pentests, and bug bounty hunting, built around how real investigations fail: anchored hypotheses, false…

NOT for educational purposes: An MCP server for professional penetration testers including STDIO/HTTP/SSE support, nmap, go/dirbuster, nikto, JtR,…

LAVA: Large-scale Automated Vulnerability Addition

An open testing platform that probes HTTP/1.1 servers against RFC 9110/9112 requirements, smuggling vectors, and malformed input handling. Add your…

Automated API security testing tool that generates tests from OpenAPI specs, fuzzes inputs, and checks for OWASP API Top 10 vulnerabilities including…

Some setup scripts for security research tools.

Curated collection of offensive security conference slide decks covering kernel and mobile exploitation, VM/container escapes, and…


Fully dockerized Linux kernel debugging environment for Linux and MacOS

The materials of "Hypervisor 101 in Rust", a one-day long course, to quickly learn hardware-assisted virtualization technology and its application…

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A Linux framework to enable userspace-defined "Virtual" PCIe card shims to enable in-host PCIe card driver development.

The fastest LoongArch sandbox