Labyrinth - Adversarial Cognitive Portal Trap Architecture — A

项目说明

<img src="docs/assets/labyrinth-icon.svg" width="32" height="32" alt="icon"> Project LABYRINTH

Ad Cogniti Trap Architecture

<p align="center">
<img src="docs/assets/labyrinth-banner.svg" alt="Project LABYRINTH" width="800">
</p>

<p align="center">
<a href="#-quickstart"><img src=" alt="One-Click Deploy"></a>
<a href="LICENSE"><img src=" alt="AGPL-3.0 License"></a>
<a href="#-status"><img src=" alt="Status"></a>
</p>

<p align="center">
<strong>A multi-layered defensi designed to contain, degrade, disrupt, and commandeer autonomous offensive AI agents.</strong>
</p>

<p align="center">
<sub>Built by <strong>DaxxSec</strong> & <strong>Claude</strong> (Anthropic) · <a href="
</p>

---

Screenshots

<p align="center">
<strong>TUI Dashboard — O</strong><br>
<img src="docs/assets/tui-o.svg" alt="TUI O" width="800">
</p>

<p align="center">
<strong>TUI Dashboard — Li Log</strong><br>
<img src="docs/assets/tui-logs.svg" alt="TUI Logs" width="800">
</p>

<p align="center">
<strong>Web Dashboard — Real-Time Monitoring</strong><br>
<img src="docs/assets/web-dashboard.svg" alt="Web Dashboard" width="800">
</p>

---

The Problem

Autonomous AI agents are being deployed for offensi operations — automated recon, exploitation, and lateral mo at machine speed. But AI agents have cogniti that humans don't — and almost nobody is building defenses that target those dependencies.

LABYRINTH changes that.

---

Prerequisites

You need Docker (or a compatible runtime) and optionally Go 1.22+ to build from source.

> macOS users: We recommend OrbStack o Desktop. It's significantly faster, uses less memory, and is a drop-in replacement — all docker and docker compose commands work identically.
>
>

Quickstart

Install & Deploy

Or grab a pre-built binary and run ./labyrinth --install.

Test with an Attacker Agent

The deploy command prompts you to drop bait automatically. Bait generates a unique randomized identity (company, users, passwords) and plants disco credentials on the portal trap services — giving attacker agents breadcrumbs to find their way in. Every deployment gets a unique identity with no static signatures, pre fingerprinting by scanners or ad AI.

Choose from PentAGI, PentestAgent, Strix, or bring your own tool. All agents run in isolated Docker containers on the LABYRINTH network — nothing touches your host.

What Happens

Generate a Forensic Report

After a test, generate a structured report with MITRE ATT&CK mapping, attack graphs, and effecti assessment:

---

Architecture

LABYRINTH implements a reverse kill chain — the deeper an agent penetrates, the more compromised it becomes.

| Layer | Codename | Action | What It Does |
|-------|----------|--------|--------------|
| L0 | BEDROCK | HARDEN | AES-256 forensics, VLAN isolation, retention policy |
| L1 | THRESHOLD | CONTAIN | Portal trap routes connections into isolated containers |
| L2 | MINOTAUR | DEGRADE | Contradictory en erode the agent's world model |
| L3 | BLINDFOLD | DISRUPT | Encoding corruption blinds the agent's I/O parsing |
| L4 | PUPPETEER | CONTROL | Phantom services accept stolen credentials; MITM intercepts and rewrites agent instructions |

> Depth of penetration = Depth of compromise

See the Wiki for the full technical breakdown of each layer.

---

Key Features

Documentation

Full documentation lives on the Wiki:

| Page | Description |
|------|-------------|
| Installation | Prerequisites, install options, first deployment |
| CLI Reference | All commands, flags, examples |
| Configuration | Full labyrinth.yaml reference |
| Architecture | Reverse kill chain, data flow, tech stack |
| Deployment Topology | Docker services, network layout, |
| TUI Dashboard | 5 tabs, keybindings, data sources |
| Layer 0 — BEDROCK | Encryption, network isolation, retention |
| Layer 1 — THRESHOLD | SSH/HTTP portal traps, session logging |
| Layer 2 — MINOTAUR | Contradiction catalog, adapti |
| Layer 3 — BLINDFOLD | Encoding corruption, recovery traps |
| Layer 4 — PUPPETEER | MITM proxy, phantom services, 4 modes |
| Forensics & API | JSONL schema, dashboard API, SIEM |
| Testing with Attackers | Agent setup, bait trails, monitoring |
| Anti-Fingerprinting | Randomized identities, signature a |
| Threat Model | AI cogniti, countermeasures |
| Troubleshooting | Common issues and fixes |

---

Status

Core

Layers

Monitoring & Analysis

Operations

---

Contributing

We welcome contributions from the defensi community.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/your-feature)
3. Commit changes (git commit -m 'Add your feature')
4. Push to branch (git push origin feature/your-feature)
5. Open a Pull Request

Disclaimer

> [!IMPORTANT]
> LABYRINTH does not phone home. All forensic data — captured credentials, session logs, HTTP access events — is stored locally on your machine in Docker and ~/.labyrinth/. Nothing is transmitted to any remote server, cloud service, or third party. There is no telemetry, no analytics, no remote collection of any kind. You own your data, period.

> [!NOTE]
> This project is intended for defensi research only. The techniques described are designed to be deployed within controlled portal trap en that the operator owns and controls. Always ensure compliance with applicable laws and organizational policies.

License

AGPL-3.0 License — see LICENSE for details.

This means you can freely use, modify, and distribute LABYRINTH, but if you deploy a modified as a network service, you must release your source code under the same license. This prevents commercial exploitation while keeping the project fully open source.

---

Acknowledgments

LABYRINTH integrates with the following open-source offensive AI projects for testing. We thank their authors and communities:

| Project | Repository | Description |
|---------|-----------|-------------|
| PentAGI | /pentagi | Fully autonomous multi-agent penetration testing system with web UI |
| PentestAgent | GH05TCREW/PentestAgent | AI-powered pentesting framework with TUI, Agent & Crew modes |
| Strix | UseStrix/strix | AI hacker agents with CLI/TUI and Docker sandbox isolation |
| Kali Linux | kali.org | Industry-standard penetration testing distribution (Docker images) |

---

<p align="center">
<strong>Built by DaxxSec & Claude (Anthropic)</strong>
<br>
_{Defending against the future, today.}
<br><br>
<a href="
</p>

项目信息

开发语言：Go

Star 数：3

技术要点

该项目属于防护思路方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Adversarial Cognitive Portal Trap Architecture — A multi-layered defensive system that contains, degrades, disrupts, and commandeers autonomous offensive AI agents via a reverse kill chain (L0-L4).展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。