Haven't touched Android research in 5 years, but Android and I just became friends again 🤝. Reported a cool 3-vulnerability chain going from untrusted -> root.
AI had a major impact on this chain, more info about that soon.
With my love for PHP exploits, going to sleep just as a WordPress Core vulnerability dropped gave me huge FOMO.
One thing is certain... it's a beautiful vulnerability.
The last year and especially the last few months have been the tipping point for me to understand how impactful AI agents are for security and vulnerability research. I used to be a bit of an AI hater, but seeing the capabilities of current models changed my mind a bit.
Stuff like trying to understand a piece of complex code or tracing code in order to get to a certain flow which sometimes can take hours is now a lot easier. Just asking an agent questions is mind-boggling.
We (+@nirohfeld) found a critical vulnerability chain in NVIDIA's Triton Inference Server (CVE-2025-23319) that can lead to full Remote Code Execution (RCE).
An unauthenticated attacker can remotely take over the server, a cornerstone of many AI/ML production environments. 🧵
A successful exploit could allow an attacker to steal proprietary AI models, intercept sensitive data, manipulate model responses, and use the server as a launchpad for further network attacks.
For a vulnerability breakdown and mitigation details, read our blog post (@wiz_io):
wiz.io/blog/nvidia-triton-cv…
This was a huge effort from the team. With every small primitive we discovered, we got closer—until we finally landed a full unauthenticated RCE. I had a ton of fun working on this research. ☸️👇
We (+@sagitz_ @ronenshh @hillai) found a series of unauthenticated RCEs in core @KubernetesIO project "Ingress-NGINX".
The impact?
From zero permissions ➡️ to complete cluster takeover 🤯
This is the story of #IngressNightmare 🧵⬇️
Throughout our research, we’ve seen many admission controllers running with high privileges. Their complex logic increases the chances of vulnerabilities—as we demonstrated with Ingress-NGINX. 🎯
With this research, we hope to raise awareness within the @kubernetesio community about this often-underestimated attack surface. ☁️⚠️
A couple of months ago, we at @wiz_io discovered a container escape vulnerability in the NVIDIA Container Toolkit, which impacts many cloud and AI SaaS providers. We're finally able to share the technical details.
wiz.io/blog/nvidia-ai-vulner…
Personally, though I’m biased 😏, this is one of the coolest container escape vulnerabilities.
youtube.com/watch?v=Om5Xyzke…
We discovered a container escape vulnerability in the @NVIDIA Container Toolkit. It allows attackers to gain full access to the host's filesystem and achieve Remote Code Execution (RCE).
Here's everything you need to know about CVE-2024-0132 🧵👇
Update to v1.16.2 of the NVIDIA Container Toolkit and v24.6.2 of the NVIDIA GPU Operator to secure your AI infrastructure.
Environments running untrusted container images are most at risk and should update immediately.
For more details about this issue, check out our blog:
wiz.io/blog/wiz-research-cri…
