
Decepticon
Autonomous LLM red team agent that plans and executes full attack chains—recon, exploitation, privilege escalation, lateral movement and C2—inside an…

Autonomous LLM red team agent that plans and executes full attack chains—recon, exploitation, privilege escalation, lateral movement and C2—inside an…

open-source pentest management built to be operated by an AI agent

CAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…

AI coding agents that can't exfiltrate secrets or merge their own PRs.

Kernel-enforced authority and runtime security for Linux systems, autonomous software, and AI agents.

DECeption with Evaluative Integrated Validation Engine (DECEIVE): Let an LLM do all the hard honeypot work!

Automating Host Exploitation with AI

My manifesto, and stories, images, and phun stuff

Reverse engineered Linux kernel driver and userspace library for the Apple Neural Engine (ANE), enabling hardware access and analysis on Linux…

Technical vulnerability analysis and proof-of-concept for CVE-2026-47630, an arbitrary dlopen via TRITON_BATCH_STRATEGY_PATH in NVIDIA Triton…

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

Paste a redacted copy of your clipboard with one hotkey. Hides API keys, tokens, passwords and PII (900+ patterns) before they reach AI chats,…

Semantic Observability for UNIX Systems - A lightweight C-based system prober with AI-powered analysis

Network and domain security auditor scanning Windows Active Directory, Linux systems, and network infrastructure with AI-powered hardening guides…

CVE-2026-45033 PoC for Claude Code, not Github Copilot. Worked for Haiku 4.5.

A PoC for CVE-2024-3660. Arbitrary Code Execution in Keras.