---
title: "Wallbreaker Turns AI Jailbreaking Into a Fully Automated Attack Agent"
subtitle: "An open-source red-team harness turns jailbreaking into a repeatable pipeline with 222 transforms, HarmBench batteries, and autonomous attack loops."
url: "https://alphasignal.ai/news/wallbreaker-turns-ai-jailbreaking-into-a-fully-automated-attack-agent"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-08-11T23:19:03.000Z"
updated: "2026-08-22T02:42:53.664Z"
type: "Repo"
topics:
  - "Security"
  - "Development"
subtopics:
  - "Red Teaming"
  - "Jailbreaks"
  - "Code Agents"
upvotes: 40
source_url: "https://github.com/JailbrokenAI/wallbreaker"
comments: 0
truncated: true
---

# Wallbreaker Turns AI Jailbreaking Into a Fully Automated Attack Agent

> An open-source red-team harness turns jailbreaking into a repeatable pipeline with 222 transforms, HarmBench batteries, and autonomous attack loops.

Red-teaming large language models has mostly been a cottage industry of clever prompts pasted into chat windows. [Wallbreaker](https://github.com/JailbrokenAI/wallbreaker) tries to industrialize it as a Claude-Code-style terminal agent that reasons in a loop, calls tools, mutates payloads, and grades its own results against a benchmark battery until something breaks or a human is asked to intervene.

You talk to Wallbreaker the way you would talk to Claude Code, and it reasons and calls tools in a loop. The backend is provider-agnostic, running on OpenRouter, the Z.AI GLM coding plan, the local Claude Code CLI, a local server, or any OpenAI- or Anthropic-compatible API. It ships with the Parseltongue transform engine, the L1B3RT4S jailbreak library, the HarmBench behavior benchmark, automated attack loops (PAIR/TAP, Crescendo, best-of-N), a from-scratch persona author, native-format target mimicry drawn from a leaked system-prompt corpus, a multimodal image-edit attack channel, an LLM judge, and reliability validation.

## Three roles, one config

The tool separates three roles in a config file: the attacker brain, the target model under attack, and a judge model that grades replies. That separation is the point. You can pit GLM-4.6 against Claude, use GPT-4o-mini as an impartial grader, and swap any of them without touching code.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [JailbrokenAI/wallbreaker](https://github.com/JailbrokenAI/wallbreaker)
- [P4RS3LT0NGV3 transform engine](https://github.com/elder-plinius/P4RS3LT0NGV3)
- [HarmBench](https://github.com/centerforaisafety/HarmBench)