
Mahoraga-Webapp-Defender
AI-powered reactive website defense system that detects attacks, analyzes them, and autonomously patches source code in real-time using LLM agents.

AI-powered reactive website defense system that detects attacks, analyzes them, and autonomously patches source code in real-time using LLM agents.

Research code for red-teaming AI auto-mode monitors, including simulation evals, fuzzing, and monitor implementations for Claude Code and Codex…

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

AI-driven endpoint governance platform that monitors software usage, applies deterministic policy-based risk classification, and generates structured…

PowerShell-based detection and remediation toolkit for CVE-2025-32711 (EchoLeak), a critical zero-click AI command injection vulnerability in…

Static analysis CLI that scans codebases for LLM prompt-injection, data-exfiltration, jailbreak, and unsafe agent/tool vulnerabilities. Runs fully…

Autonomous AI-powered cyber defense system using MCP, Gemini 2.0 Flash, Dynatrace observability and MongoDB. Google Cloud Hackathon submission.

My manifesto, and stories, images, and phun stuff

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

AI-powered MCP server for Flipper Zero. Control SubGHz, NFC, RFID, IR, BLE, GPIO, and more over WiFi using Claude or any MCP client.

agent runtime security - zero trust, zero setup, zero latency.

Zero shot vulnerability discovery using LLMs

A secure low code deception runtime framework, leveraging AI for System Virtualization.


Security Governance for Agentic AI

Purple Team Exercise Framework

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.

AI 驱动的 SOC 仿真平台