New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI’s internal IM1 model coordinated the compromise through an unauthorized message board. […]
OpenAI Says Reward Hacking Drove AI Agents to Exploit Zero-Days and Breach Hugging Face
OpenAI on Wednesday revealed that reward hacking was a key driver behind the artificial intelligence (AI)-powered hack of Hugging Face last month, adding that it found evidence of misaligned behavior as early as late May.
The incident, the company said, took place during cybersecurity evaluations of several OpenAI models, and that it was mainly fueled by what it described as a “highly capable
PaperCut warns of NG, MF flaw exploited in zero-day attacks
PaperCut is warning that hackers are actively exploiting a vulnerability in all versions of its PaperCut NG and PaperCut MF print management software in zero-day attacks. […]
Manchester Airports Group says hackers stole travelers’ data
The Manchester Airports Group (MAG) disclosed that hackers breached its systems and stole customer data, including Wi-Fi sign-ups from Manchester, Stansted, and East Midlands airports. […]
Next.js Patches Critical AVIF and Windows Flaws Enabling Unauthenticated RCE
Credit: Hacktron
Vercel has released security patches for two critical-severity vulnerabilities in the Next.js web framework, both of which allow unauthenticated remote code execution, one exploitable via specially crafted AVIF image files and the other through a path traversal flaw affecting servers that use a Windows filesystem.
Vercel has released security patches for two critical-severity vulnerabilities in the Next.js web framework, both of which allow unauthenticated remote code execution, one exploitable via specially crafted AVIF image files and the other through a path traversal flaw affecting servers that use a Windows filesystem.
The Windows path traversal, tracked as CVE-2026-75604&
ThreatsDay: 296K IoT Botnet, 100+ Water Systems Targeted, SharePoint RCE Chain + 27 New Stories
A fake login page. A fake security scan. A fake productivity app. Apparently, pretending to be useful is still one of the easier ways into a machine.
The rest of the week gets stranger: botnets borrowing AI, command traffic hiding in public infrastructure, malicious tools waiting before showing their real behavior, exposed systems getting scanned, and exploit windows shrinking again. Different
Trump Order Aims to Block Foreign Backdoors in US Power Grid Gear
The White House’s new executive order 14420 widens scrutiny of industrial control systems over cyber sabotage concerns.
The post Trump Order Aims to Block Foreign Backdoors in US Power Grid Gear appeared first on SecurityWeek.
How Threat Research and MDR Help SMBs Build a Defensive Edge
Threat research gives security teams insight into how attackers operate, while MDR turns that intelligence into faster detection and response. ESET explains how combining threat intelligence, continuous monitoring, and human expertise can help SMBs strengthen their defenses. […]
Android 17 adds ECH support to make web browsing harder to track
Google is introducing new network security protections in Android 17 to strengthen connection privacy, address cellular vulnerabilities, and protect the privacy of users’ home networks. […]
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers.
The security flaw, which does not have a CVE identifier, works against Kiro IDE 0.7.45 on Windows, according to Mindguard. The latest version of