Noteworthy stories that might have slipped under the radar: Siemens ROX II industrial switch vulnerabilities, Russian Zimbra webmail espionage campaign, Stadler Rail ransomware extortion attempt. The post In Other News: Dolphin X AI-Powered Malware, Car Anti-Theft Device Hack, 400 Linux Kernel Flaws appeared first on SecurityWeek.
Researchers H0j3n and Aniq Fakhrul published a working exploit on July 24 that lets a low-privileged Active Directory user obtain a certificate for a Domain Controller and authenticate as that machine. They codenamed the flaw Certighost. Because Domain Controller accounts carry directory replication rights, the resulting Kerberos credential can retrieveRead More »Certighost Exploit Lets Low-Privileged Active Directory Users Impersonate a Domain Controller
The company has raised a total of $49 million in funding, including from Battery Ventures, Accel and Foundation Capital. The post AegisAI Raises $36 Million for AI-Powered Email Security appeared first on SecurityWeek.
Cybersecurity researchers have disclosed a critical vulnerability in OpenAI’s ChatGPT Workspace Agents that could have allowed a single phishing link to stealthily build, authorize, and deploy an autonomous artificial intelligence (AI) agent inside a victim’s organization. The vulnerability has been codenamed AgentForger by Zenity Labs. The issue has since beenRead More »ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link
A crafted SVG submitted to Bing’s image search ran commands as NT AUTHORITYSYSTEM on Microsoft’s production image-processing workers, and as root on the Linux machines in the same fleet. XBOW’s testing got the same result on workers across different hosts and network ranges, so the problem sat in Bing’s imageRead More »Bing Images Flaws Let Crafted SVGs Run Commands as SYSTEM on Microsoft’s Servers
AI agent security is moving through a familiar maturity curve: adoption, then visibility, and finally, control. But what we’ve collectively discovered is that enforcing least privilege for AI agents is harder than we ever imagined. This is why there are so many approaches, from prompt filtering to identity-layer access controls.Read More »Seeing AI Agents Is Not Enough. Security Teams Must Enforce What They Can Do
Industry professionals debate whether it represents a lab containment failure or an unprecedented agentic capability milestone. The post Industry Reactions to OpenAI Models Hacking Hugging Face: Feedback Friday appeared first on SecurityWeek.
This essay was written with Barath Raghavan, and originally appeared in IEEE Spectrum. Major benchmarks measure what AI can do. None measure whether it does what you mean: the distance between what you ask an AI to do and the unspoken assumptions about how you want the AI to doRead More »Why AI Needs a “Genie Coefficient”
Someone installed a popular AI assistant on a rented server, switched off the setting that makes it ask permission before running risky commands, and pointed it at Thailand’s Ministry of Finance, which runs the country’s treasury and tax collection. The agent then worked through the ministry’s network on its own,Read More »Hacker Runs Hermes AI Agent Unattended for Post-Exploitation at Thai Finance Ministry
The threat actors behind the Golden Chickens malware-as-a-service (MaaS) ecosystem have resurfaced with four new malware families, indicating that the operators are showing no signs of stopping despite extensive public disclosures into their inner workings. The malware families in question are: TinyEgg, ChonkyChicken, a modularized variant of ChonkyChicken, and aRead More »Golden Chickens Resurfaces With Four New Malware Families and Modular Implants
