Multiple zero-day vulnerabilities in self-hosted Artifactory after OpenAI’s frontier models autonomously exploited them to escape a sandboxed research…
Leaky BMCs, Claude finds encryption flaws, Google’s new names
Thousands of server BMCs leak password hashes Claude finds flaws in encryption Google gives old threat actors new names Get the show notes here:…
Sensitive, Bizarre Anthropic Claude Chats Exposed Online
Anthropic limits accessibility after hundreds of personal chats with Claude bot exposed through public searches
Infoblox enters EASM market with attack surface and supply chain risk tools
Infoblox has announced its entry into the external attack surface management (EASM) market. Together, with the introduction of Supply Chain Intelligence,…
Bank of Baroda Confirms Data Breach After Employee Email Account Compromised
Bank of Baroda has confirmed a cybersecurity incident involving the compromise of an employee’s email account, which allowed unauthorized access to…
Reco enhances AI Runtime with browser-based AI security and automated remediation
Reco has announced an expansion of AI Runtime, a core component of the Reco Platform. This update adds browser-based enforcement, real-time prompt…
IT Security News Hourly Summary 2026-07-29 09h : 6 posts
6 posts were published in the last hour 7:2 : OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach 6:31 : Hackers Are Hiding Commands in Emails to Trick the AI Systems Protecting You 6:31 : An…
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…
Hackers Are Hiding Commands in Emails to Trick the AI Systems Protecting You
Attackers are beginning to hide malicious instructions inside ordinary emails, documents, calendar invites, and online advertisements. The goal is not…
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…
Apple Releases Security Updates Patching Nearly 200 Vulnerabilities Across macOS, iOS, iPadOS, and Safari
Apple has released security updates for its operating systems, addressing nearly 200 vulnerabilities. Thank you for being a Ghacks reader.
ShinyHunters Claims Ernst & Young Hack
Ernst & Young previously confirmed that personal and financial information was stolen from a third-party management platform.
Malicious npm Packages Deploy Cross-Platform RAT Targeting Alibaba Developers
A cluster of malicious npm packages has been used to deliver a cross-platform remote access trojan against developers who use Alibaba-related tools. The…
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…
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. The systems stay…
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…
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 13.56 MHz. The…
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…
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,…
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…
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…
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. Run either one past a machine…
Claude AI Autonomously Discovers Cryptographic Weaknesses That Escaped Expert Review
Researchers at Anthropic reported that Claude Mythos Preview autonomously discovered new cryptographic attacks against
IT Security News Hourly Summary 2026-07-29 06h : 3 posts
3 posts were published in the last hour 4:2 : First-Ever Fully Autonomous AI Cyberattack Exploits 0-Day Flaws to Infiltrate Hugging Face 4:2 : NGINX Heap Overflow Flaw Could Let Unauthenticated Attackers Execute Arbitrary Code 4:2 : OpenAI Open-Sources Codex…