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 […]

# Escaping Linux Sandboxes via PipeWire (CVE-2026-5674) 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 […]

# Exploiting Titan Quest Titan Quest is a hack-and-slash video game released in 2006. In 2016, THQ Nordic released an _Anniversary Edition_. In the version provided by GOG, several development tools are installed with the game. These allow for the creation of new maps, items, and effects. This article details […]

I recently ran into an interesting behavior on Windows that I found unintuitive so I figured other people may want to know about it too. An application can call `AddClipboardFormatListener` to register a callback that gets called whenever the clipboard contents change, like when you copy a file or some […]

# When AI Makes 0-Days Feel Like N-Days **Table of Contents** ## Introduction After my n-day analysis on net/tls bugs and exploit writing for a patched net/rxrpc bug, I moved on to 0-day bug hunting. With the help of AI, I found a UAF bug in net/sched, and went about […]

(c) WUNDERWUZZI 2018-2026 Disclaimer: Penetration testing requires authorization from proper stakeholders. Information on this blog is provided for research and educational purposes to advance understanding of attacks and countermeasures to help secure the Internet. | Privacy

Automatic Program Repair (APR) has emerged as a critical technology for autonomously addressing software vulnerabilities. While recent advances in Large Language Models (LLMs) have enabled sophisticated agentic APR systems, existing approaches still struggle to generate patches for vulnerabilities whose root causes are difficult to identify. This happens because prior methods […]