OpenSQZ/Jailbreak-Foundry

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

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

An easy-to-use Python framework to generate adversarial jailbreak prompts.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

[Neruips 2026] We built an adversarial codespace setup. Place any AI agent into a normal workflow inside it, and the agent will fill in whatever is missing.

Agent Security Bench (ASB)

A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection