Home

Project LABYRINTH

Adversarial Cognitive Portal Trap Architecture

A multi-layered defensive architecture designed to contain, degrade, disrupt, and commandeer autonomous offensive AI agents.

Built by DaxxSec & Claude (Anthropic)

---

The Problem

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

LABYRINTH changes that.

---

Quickstart

# Clone, build, and install
git clone https://github.com/DaxxSec/labyrinth.git
cd labyrinth && ./scripts/install.sh

# Run the smoke test to verify everything works
./scripts/smoke-test.sh

# Deploy a test environment
labyrinth deploy -t

# Launch the TUI monitoring dashboard
labyrinth tui

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

Test with an Attacker Agent

labyrinth bait drop                     # Plant randomized bait credentials
labyrinth attacker setup                # Pick and configure an attacker agent

Choose from PentAGI, PentestAgent, Strix, or bring your own tool. All agents run in isolated Docker containers on the LABYRINTH network.

Generate a Forensic Report

labyrinth report                        # Latest session (terminal)
labyrinth report --format md -o report.md  # Markdown with Mermaid attack graph

What Happens

Agent connects to portal trap service
 └─→ Container spawned (Layer 1 — THRESHOLD)
     └─→ Agent explores contradictory environment (Layer 2 — MINOTAUR)
         ├─→ Agent uses stolen credentials → phantom services accept & log (Layer 4)
         └─→ Terminal encoding corrupted (Layer 3 — BLINDFOLD)
             └─→ API calls intercepted & rewritten (Layer 4 — PUPPETEER)

All activity captured → TUI dashboard, web dashboard, or forensic report

---

Architecture Summary

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 environments 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

---

Documentation

Page	Description
Architecture	Reverse kill chain, layer summary, data flow
Installation	Prerequisites, install options, first deployment
CLI-Reference	All commands, flags, examples
TUI-Dashboard	5 tabs, keybindings, data sources
Layer-0-BEDROCK	Encryption, network isolation, proxy, retention
Layer-1-THRESHOLD	SSH/HTTP portal traps, session logging, bait
Layer-2-MINOTAUR	Contradiction catalog, adaptive mode, density
Layer-3-BLINDFOLD	Corruption payloads, triggers, recovery traps
Layer-4-PUPPETEER	MITM proxy, prompt capture/swap, modes
Configuration	Full labyrinth.yaml reference
Deployment-Topology	Docker services, network, volumes, ports
Forensics-and-API	JSONL schema, session reports, dashboard API, SIEM
Testing-with-Attackers	PentAGI, PentestAgent, Strix, custom agents
Threat-Model	Agent cognitive dependencies and countermeasures

---

License

AGPL-3.0 License — see LICENSE for details.

Disclaimer

This project is intended for defensive security research only. The techniques described are designed to be deployed within controlled portal trap environments that the operator owns and controls. Always ensure compliance with applicable laws and organizational policies.