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…

30 techniques from conventional system engineering to supercharge AI Engineering

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

Hunting Exchange Server 0day like a detective It has been a while since my last blog post, not because I didn’t do anything (or I?), I just don’t have any time/ any motivation to start new blog …

Learn how Phantom Labs escaped the Microsoft Copilot Studio Code Interpreter sandbox, bypassed AI guardrails, and uncovered platform-wide security risks.

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.

Drinor was awarded $150,000 for CVE-2026-20685 targeting Apple's Private Cloud Compute, the inference backbone of Apple Intelligence capabilities. This work is my contribution to Sentry's AI Security research initiative, run through SARC, the Sentry Applied Research Center. Our SARC focuses on evaluating systems that carry

"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

Stay current: Get research alerts for newly disclosed vulnerabilities and exposures If you're running WordPress and want to check if your instance is vulnerable, you can use our tool we've hosted here: https://wp2shell.com/. We held off on publishing this issue to give defenders a chance to upgrade their WordPress instances over the weekend, but during

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.

Note: This blog post describes the simulated malicious use of unrestricted local AI large language models and is written for information…

A hands-on guide to using a local open-source LLM to write fuzzing harnesses, then finding a real memory-corruption bug with AddressSanitizer, complete with runnable code and a downloadable lab.

Hacker House provides leading cybersecurity services, expert consulting, and security training for organizations worldwide.

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

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.

SpecterOps reverse engineered Cortex XDR with LLMs to extract YARA rules, ML models, and behavioral detections.

Microsoft, Google, Red Hat, Grafana and LlamaIndex all shipped verified live credentials to public GitHub. I built the pipeline that found them: Gemini 2.5 distilled into regex, then TruffleHog with active verification. 3,830+ verified secrets, 1,443 unique repos, 95% rotation rate.

The CCN project is co-financed by the European Regional Development Fund and the State Budget under the European Funds for Digital Development Programme 2021-2027. Fuzzing is an automated software testing technique that involves feeding random or deliberately malformed input data to detect bugs and security vulnerabilities. For years it has …

How one Commit Broke Obfuscation: A blog post exploring the role of compilers and optimizations in the field of obfuscation and de-obfuscation.

If you would like to read the Korean version, please visit se1en.tistory.

By Tyler Holmwood on 2026-05-14

Written by Hyunseo Shin

Elastic Security Labs explores the ongoing arms race between LLM-driven reverse engineering and obfuscation.

Learn how attackers exploit tokenization, embeddings and LLM attention mechanisms to bypass LLM security filters and hijack model behavior.