From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

Generative AI systems are increasingly used not only to produce content but also to retrieve data, invoke tools, and execute actions. This work examines the security and safety implications of that shift across content-level, model-level, and agentic threats. We analyze how attacker access...

CVE-2026-8568

CVE-2026-8568 is a Chromium/Google Chrome vulnerability described as insufficient policy enforcement in AI, allowing a renderer process–level attacker to bypass Site Isolation via a crafted HTML page. Reports cite remote code execution, DoS, or information disclosure as potential impacts. Debian ...

The time of much patching is coming

Welcome to this week's edition of the Threat Source newsletter. Many solutions have been proposed to reduce software bugs: zero-defect mandates, pair programming, formal methods, and mathematical software proofs. The reality is that software engineering is hard. Identifying and fixing bugs before...

ThreatsDay Bulletin: PAN-OS RCE, Mythos cURL Bug, AI Tokenizer Attacks, and 10+ Stories

Everything is still on fire. This week feels dumb in the worst way — bad links, weak checks, fake help desks, shady forum posts, and people turning supply chain attacks into some cursed little game for clout and cash. Half of it feels new. Half of it feels like crap we should have fixed years ago...

EUVD-2026-30303

PyTorch Lightning is a deep learning framework to pretrain and finetune AI models. Versions 2.6.2 and 2.6.2 have introduced functionality consistent with a credential harvesting mechanism...

Personal AI Infrastructure 5.0.0

PAI is a Personalized AI Platform designed to magnify your capabilities. It's designed for humans most of all, but can be used by teams, companies, or Federations of Planets desiring to be better versions of themselves. The goal of the project is to get people working with AI and lower the bar...

HCL AION 安全漏洞

HCL AION is an AI lifecycle management platform developed by the Indian company HCL. HCL AION has a security vulnerability; this vulnerability arises from certain operations that may trigger interactions with external parties, potentially leading to the accidental disclosure of sensitive...

Toward Securing AI Agents like Operating Systems

Autonomous agents based on large language models LLMs are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper integration into user environments. At the same time, these agentic...

WhatsApp Adds Meta AI Chats That Are Built to Be Fully Private

The company says its new Incognito Chat allows you to use its AI chatbot without anyone else—including Meta—being able to access your conversations...

Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday

Microsoft has unveiled a new multi-model artificial intelligence AI-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview. MDASH, short for m ulti-mod el a gentic s canning h...

Characterizing AI-Assisted Bot Traffic in Darknet Data: Implications for ICS and IIoT Security

The rise of automated scanning tools and AI assisted reconnaissance agents has significantly altered internet background traffic patterns, threatening the baseline assumptions underlying intrusion detection systems IDS deployed in critical infrastructure networks. This paper characterizes the...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

Webinar: What the Riskiest SOC Alerts Go Unanswered - and How Radiant Security Can Help

Why do the Riskiest SOC Alerts Go Unanswered? Security operations teams are drowning in alerts. But the real problem isn't always alert volume; it's the blind spots. The most dangerous alerts are the ones no one is investigating. A recent report from The Hacker News examined why certain high-risk...

Why Agentic AI Is Security's Next Blind Spot

Agentic AI is already running in production environments across many organizations today. It is executing tasks, consuming data, and taking actions — most likely without meaningful involvement from the security team. The industry conversation has largely framed this as a question of policy: allow...

ISPB

🛡️ AI-powered Security Scanner Platform A next-generation...

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.3 (Spyre)

Red Hat AI Inference Server 3.3.3 Spyre is now available. Red Hat® AI Inference Server...

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code...

PT-2026-40081

Uncontrolled search path for some AI Playground software before version 3.0.0 alpha within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with an authenticated user combined with a high complexity attack may enable escalation of privilege. This...

This Week in Spring - May 12th, 2026

Hi, Spring fans! As I write this I am in Miami, FL at the CodeRemix.ai show, focused on the wide and wonderful world of OpenRewrite and Moderne. I've got a talk to give so let's dive right into it! a quick note about the upcoming release train dates in last week's installment of A Bootiful Podcas...

Google Chrome 安全漏洞

Google Chrome is a web browser developed by Google Inc. Versions of Google Chrome prior to 148.0.7778.168 contained a security vulnerability. This vulnerability stemmed from insufficient policy execution in the AI component, which could allow remote attackers who have breached the rendering proce...