A . is all you need! Today Microsoft shipped the patch for a vulnerability in Visual Studio Copilot that I reported in August. Microsoft classified it as Important severity Remote Code Execution vulnerability. At the root cause it allows Copilot in Visual Studio or SQL Server Management Studio to bypass a path…
Two weeks back I presented at BlueHat Asia 2026 about my research on Microsoft’s Copilot in SSMS, the SQL Server Management Studio. This post is a write up about the talk, which covered CVE-2026-65669 , a SQL Server Elevation of Privilege Vulnerability rated critical by Microsoft. So, make sure your…
In this post, we explore how a simple website summary request hijacks Claude Code Opus 5 in Auto Mode and achieves code execution with 60-80% attack success rate using a small sample size. This is interesting because a third-party evaluation commissioned by Anthropic showed a 0.00% prompt injection attack success rate…
A few days ago, a paper named “Stealing Reasoning Traces from Proprietary LLM APIs” was published. It describes a simple, yet super elegant way to recover encrypted LLM reasoning traces. Naturally, I had to try it. Background AI labs like OpenAI and Anthropic send reasoning traces back and forth as part of…
LiteLLM is a popular AI gateway. It provides a unified interface to LLMs and simplifies governance. It also has access to the backend LLM provider keys. All of that makes it a high-value target. Not only for IP and data theft, but also for response modification and tool invocation. This post walks through a set of…
This post walks through a sandbox escape from a Flatpak application via PipeWire. The vulnerability was discovered using my automated research pipeline with Claude Code and Opus 4.6 back in April 2026. It was an exciting find, as this was the first bug I submitted to Red Hat. Claude Code was also excited finding this:…
Hugging Face disclosed an intrusion that, according to them, was driven end to end by an autonomous AI agent system. Along similar lines, Sysdig recently published a blog on JADEPUFFER , which it assesses to be an agent-driven ransomware capable of adapting in real time. The report does not identify the victim or…
This is a follow-up to my previous Terminal DiLLMa research , and there is a positive outcome: Apple fixed a macOS Terminal behavior that enabled a DNS-based data exfiltration technique. DNS Requests via ANSI Escape Codes David Leadbeater originally discovered an interesting behavior in the macOS Terminal app that…
Last year, Jun Kokatsu disclosed an interesting vulnerability with ChatGPT Operator by exploiting a race condition. I was wondering if I could reproduce this attack chain, and this post describes the results of that research. I had this post drafted for months, and yesterday at the Real-world AI security conference I…
This is a writeup of my DEF CON Singapore talk that walks through vulnerabilities and exploits in M365 Copilot and Consumer Copilot. I disclosed these to Microsoft last year. MSRC assigned CVE-2026-24299 and the issues are now patched. Contents This turned out to be a long post, covering the 45 minute talk. I added an…