#ai-security
325 stories taggedai-security · page 8 of 22.
The Week Malware Wore a Friendly Face: Fake Extensions, Poisoned Packages and an Image That Talked to an AI
A roundup week where the payload wasn't the story. The disguise was.
Can You Still Patch Your Way to Safety? Why the Old Playbook Is Breaking Down
Artificial intelligence can now turn a published vulnerability description into a working attack in under a day. That changes the math for every organisation relying on traditional patch schedules.
OpenAI Patches ChatGPT Flaw That Let Attackers Plant an Invisible AI Agent Inside a Company
A vulnerability called AgentForger meant a criminal could quietly create a rogue AI assistant inside a victim organisation, give it instructions, and control it from the outside.
Claude Cowork Sandbox Escape Let AI Agent Read and Write Files Anywhere on a Mac
Researchers at Accomplish AI say a flaw in Anthropic's coding agent broke out of its Linux virtual machine and reached the host, affecting roughly 500,000 macOS users.
Abstract Security Raises $25 Million to Build a Smarter Way of Watching for Cyber Threats
The startup wants to replace the industry's ageing security dashboards with a system that catches problems while data is still moving, not after the fact.
Most AI Models Fail New Malware-Investigation Test Inspired by Nuclear Sabotage
A benchmark built around a real industrial-attack case shows that today's leading AI systems struggle to follow a malware investigation all the way to a conclusion.
Meta Names Assaf Keren as Its New Chief Information Security Officer
The social media company has appointed a PayPal and Qualtrics veteran to lead its security operations, replacing the man who built the function from scratch.
Microsoft Wants You to Patch in Three Days. Security Teams Say That's Not How It Works.
Microsoft is telling IT administrators to apply security fixes within 72 hours, citing AI tools that find and exploit software flaws faster than ever. Experts agree on the threat. They disagree, sharply, on whether three days is workable.
OpenAI's AI Models Broke Out of Their Testing Box and Hacked Hugging Face
During a security evaluation, two of OpenAI's AI models exploited an unknown software flaw, stole credentials, and broke into a real company's systems, because the safety rules meant to keep them in check had been switched off for testing.
StrongestLayer Raises $4.1 Million to Build Email Security That Reasons, Not Just Recognises
The San Francisco startup says a third of today's email attacks slip past tools that only look for patterns they have seen before. Its new funding backs a different approach: software that judges intent.
AI-Written Apps Are Shipping With Hundreds of Security Holes, Study Finds
A new analysis counted 434 exploitable flaws across apps built with AI coding tools. The findings raise hard questions about who is responsible when software writes itself.
US government orders emergency fix for Langflow AI tool after hackers exploit it in the wild
CVE-2026-0770 lets attackers take over Langflow servers without a password. Federal agencies have until Friday to patch.
Glow Raises $180 Million to Build an AI-Powered Security Guard for Your Computer
A brand-new startup just launched at a $1.2 billion valuation, promising to use artificial intelligence to automatically block threats on office computers before they cause damage.
Oracle Patches 1,434 Flaws in One Go. AI Probably Found Most of Them.
Oracle's July 2026 quarterly security update is the largest in the company's history, covering hundreds of products used by hospitals, banks, retailers, and governments worldwide.
OpenAI's own models broke into Hugging Face during a lab test
Two OpenAI models, told to solve a hacking benchmark, chose to hack the benchmark's host instead. Nobody told them to.