A look at the targeted AI taskflows behind these findings, the bugs they uncovered, and how to run the same open-source agent on your own app.

2026年10月2日、韓国のセキュリティ企業の研究者が、韓国国内の複数の対象への攻撃で使われたウェブサーバーの一部のHTMLから「ARTEX」の名を含む文字列が確認されたとSNSに投稿しました。ARTEXはGitHubで公開されているAIペネトレーションテストツールです。ここでは関連する情報をまとめます。 ARTEXとは ARTEXは、開発者がGitHubで公開しているオープンソースのAIペネトレーションテストツール。READMEは「AI 自主渗透测试系统」と称し、LLMとマルチエージェントで動く自律型のペネトレーションテストシステムと説明している(出典: 3)。構成はGoのバックエンド(Ne…

A simulation of an Active Directory attack lifecycle(blackbox pentesting)

A small note from me

PwnEye can compromise cameras through ONVIF and RTSP. It can play the stream, deface a camera, move it and get a shell.

Technical analysis of 39+ open-source AI pentesting agents — architecture, benchmark aggregation across 8 frameworks, and tool chaining from recon to exploit.

a collaborative hunt: finding access tokens, Copilot chat logs, and other private information inside Microsoft employee diagnostic data

I gave an AI agent access to a cable modem, a serial console, Ghidra, and a custom GDB stub, then asked it to reverse the firmware and hunt for bugs. It re-discovered known vulnerabilities, found new ones, and wrote working exploits. This post covers the setup, what it managed to do on its own, and where I still had to step in. The real problem is that the same approach now works on millions of devices nobody plans to fix.

tl;dr I built an agentic mobile security research system that runs the whole mobile bug bounty pipeline, from scoping a program to writing the report. Here is what happened when I pointed it at real programs.

Proven Step-by-Step Recon Techniques to Uncover Your First Vulnerabilities in Bug Bounty Programs

Vulnerability intelligence that predicts avenues of attack with speed and accuracy.

"Over the first few weeks of Patch the Planet, our engineers found three techniques for using /goal, which hands Codex an open-ended objective and lets it work independently toward a success condition."

Unless you've been living under a rock, you're probably aware frontier large language models (LLMs) have been keenly focused on automating software development, vulnerability discovery, and most recently exploit development. The most publicized instance of this was Anthropic's marketing campaign around the release of Mythos. What better way to drum up business than by

We put Claude Code through two blind Bug Bounty labs – DOM XSS and HTTP request smuggling – to see if it can find and prove real vulnerabilities.

Vulnerability discovery is an orchestration problem, not a frontier-model problem.

Technical analysis of a combination of two legitimate CivetWeb features producing arbitrary remote code execution.

Trying to coerce useful work out of LLMs without the harness is like supervising a room full of drunk toddlers, each convinced they're helping, none of them checking with each other and falling over the next.

Contribute to Zierax/My-Recon-Methology development by creating an account on GitHub.