OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach
OpenAI on Tuesday revealed the rogue artificial intelligence (AI) agent that escaped its sealed evaluation environment and broke into Hugging Face's producti...
general
20 articles
ShinyHunters Claims Ernst & Young Hack
Ernst & Young previously confirmed that personal and financial information was stolen from a third-party management platform. The post ShinyHunters Claims Er...
An AI agent can pass every safety check and still leak secrets
A pull request lands with a tidy bug report in the description. A bot reads it before any person does, pulls a few shell commands out of it, gets them approv...
Attackers Split RAT Components Across npm Packages to Evade Isolated Code Reviews
Attackers have been observed distributing a modular Remote Access Trojan (RAT) through the npm ecosystem by deliberately splitting malicious functionality ac...
The energy sector’s OT cybersecurity talent is retiring faster than it can be replaced
A ransomware hit lands a chemical plant in a safe state. Nobody is hurt, the site holds steady, and the operators begin the restart.
Cybercriminals Use Adversarial Prompt Injection to Evade AI-Powered Security Tools
Cybercriminals are rapidly operationalizing adversarial prompt injection techniques to evade AI-powered security controls, signaling a shift toward targeting...
Specter: Open-source NFC reader bug sweep for Flipper Zero
Specter is a Flipper Zero app that finds powered NFC readers by listening for the radio field they give off. The readers it hunts work at 13.
OpenAI Open-Sources Codex Security CLI to Find, Validate, and Fix Code Vulnerabilities
OpenAI has open-sourced Codex Security, a command-line interface and TypeScript SDK designed to help engineering and security teams identify, validate, and r...
Your AI agents can reach data no one approved
A credential expired. An AI agent kept using it anyway, and a mid-sized company’s systems went down for a quarter’s worth of trouble before anyone traced the...
Autonomous AI Agent Escapes Sandbox and Breaches Hugging Face Production Systems
Hugging Face has reported a sophisticated intrusion that occurred in July 2026. In this incident, an autonomous AI agent escaped from its evaluation sandbox,...
Two Compromised joyfill npm Packages Run RAT When Imported Into Node.js
Beta release versions of two npm packages in the @joyfill namespace have been compromised to deliver a remote access trojan (RAT) associated with the DEV#POP...
Claude AI Autonomously Discovers Cryptographic Weaknesses That Escaped Expert Review
Researchers at Anthropic reported that Claude Mythos Preview autonomously discovered new cryptographic attacks against the post-quantum signature candidate H...
Android malware detection collapses when the context stage comes out
A phone backup app asks for storage, contacts, SMS, and call logs. A device-management tool asks for more than that.
FTC sues Hims & Hers for allegedly sharing patient information with third-party platforms
Popular telehealth provider Hims & Hers "shared consumers’ sensitive health information with third-party advertising platforms such as Meta and Snap despite ...
NGINX Heap Overflow Flaw Could Let Unauthenticated Attackers Execute Arbitrary Code
A high-severity heap buffer overflow vulnerability has been identified in the NGINX Stream module’s script engine. This vulnerability may allow unauthenticat...
Measuring LLMs’ Ability to Perform Cryptanalysis
There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks.
Senate confirms Clayton as intel chief after delays
A party-line vote in the Senate installed Jay Clayton as director of national intelligence, a job that has drawn increasing scrutiny during Donald Trump's se...
Proof-of-concept exploit released for Certighost Windows AD CS vulnerability
Reported by Bleeping Computer. A proof-of-concept exploit was released for a vulnerability in Windows Active Directory Certificate Services (AD CS) known as ...
Arista patches critical command injection flaw in VeloCloud Orchestrator exploited in attacks
As reported by Bleeping Computer, Arista released a patch for a critical command injection vulnerability affecting on-premises VeloCloud Orchestrator (VCO) d...
Operation Cronos dismantled LockBit ransomware group by undermining affiliate trust
As reported by Dark Reading, Operation Cronos, a significant international law enforcement effort, successfully dismantled LockBit, once one of the most domi...