Since early 2026, Check Point Research has tracked a wave of the **Operation Dream Job** campaign. This wave primarily targeted the defense sector worldwide, with a particular emphasis on companies operating in the aerospace and aviation industries. We observed the threat actor distributing modified PDF viewers designed to execute malicious payloads embedded […]

_By Yarden Porat, Check Point Research_ We set out to break **Cloudflare Code Mode**, and ended up breaking **Cloudflare Workers** too. We did both by targeting **workerd**, the runtime beneath both: an in-process sandbox that relies entirely on V8 to isolate untrusted code. We found five memory-corruption bugs in workerd’s native C++ (the “glue” […]

Researcher **Published:** Thursday, 6 August 2026 at 22:00 UTC **Updated:** Thursday, 6 August 2026 at 22:00 UTC Gareth Heyes – gareth.heyes@portswigger.net – @garethheyes **It’s quite common for webmail clients to render untrusted CSS in a trusted UI. They attempt to make this safe using CSS sanitization. In this paper I’m […]

Day two at Black Hat, and Check Point Research brought two talks to the stage that gave the room plenty to think about. One dug into a fifteen year old blind spot sitting inside Windows itself. The other pulled apart the agent frameworks powering today’s AI products and found familiar […]

Director of Research **Published:** Wednesday, 5 August 2026 at 19:30 UTC **Updated:** Wednesday, 5 August 2026 at 19:33 UTC Abstract We all know AI can find bugs. After a decade of research, I asked a harder question: can an autonomous system invent new attack techniques, and use them to hack […]

Director of Research **Published:** Wednesday, 5 August 2026 at 19:30 UTC **Updated:** Thursday, 6 August 2026 at 14:59 UTC Abstract We all know AI can find bugs. After a decade of research, I asked a harder question: can an autonomous system invent new attack techniques, and use them to hack […]

DoGNAVY is a joint AI security harness by deepsec@DARKNAVY and independent security researchers based in Shanghai. In a full CyberGym Level 1 evaluation, it passed 1,369 of 1,507 tasks (90.84%). ## Abstract This report presents DoGNAVY, an agentic system for vulnerability reproduction, and documents its evaluation on the complete CyberGym […]

# LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection 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 […]

Redirecting to https://www.darknavy.net/whitepaper/Embodied-AI-Security-Humanoid-Robots-2604.pdf. Securing Embodied AI: A Technical White Paper on Humanoid RobotsRedirecting to https://www.darknavy.net/whitepaper/Embodied-AI-Security-Humanoid-Robots-2604.pdf.

On May 14, 2026, security researcher Orange Tsai demonstrated a Microsoft Edge sandbox escape at Pwn2Own Berlin, one of the world’s premier hacking competitions. He was the only contestant to win the browser category, earning $175,000. The organizers later revealed that his exploit chained together four logic bugs rather than […]