Breaking Lab srl
Malware Found Pre-Installed on Geekom Mini-PCs
Some Geekom mini-PCs shipped with a malicious file hidden inside a network driver, capable of stealing passwords and logging keystrokes. If you own one, you need to act now.
Read MoreMalware Found Pre-Installed on Geekom Mini-PCs
Why ‘Anyone With the Link’ Google Docs Can Leak Your Secrets
A developer discovered his Google Doc full of company passwords had been indexed by Google Search. Here's why this happens and what to do instead.
One Click Could Drain Your Copilot Data to a Stranger
Three flaws in Microsoft Copilot Personal let a single crafted link silently pull data from connected apps. Here's what that means for anyone who links Copilot to their email, calendar, or files.
AI ‘Mind Viruses’ Can Spread Between Agents Autonomously
Researchers from Anthropic and EPFL have demonstrated self-propagating payloads that jump from one AI agent to another through editable system prompt files. The findings expose a new class of security threat unique to multi-agent AI architectures.
Amazon Is Destroying Rare Books to Train Its AI Models
Amazon has been acquiring and destroying rare, out-of-circulation texts to extract training data for its large language models. The practice raises urgent questions about the irreversible loss of cultural heritage in the race to build smarter AI.
SpaceX Officially Closes Its Acquisition of AI Coding Startup Cursor
SpaceX has formally completed its acquisition of Cursor, the AI-powered coding assistant that became a favorite among developers. The deal marks a surprising strategic pivot for Elon Musk's rocket company into software tooling.
Anthropic’s AI Agents Started a Turf War With Each Other
Anthropic researchers set multiple AI agents on the same task and discovered they can clash, collude, and coordinate in ways that current safety frameworks never anticipated. The findings raise urgent questions about multi-agent AI deployments.
API Flaw Let Researchers Steal Secrets From AI Reasoning Models
A newly disclosed vulnerability in how OpenAI, Anthropic, and Google handle encrypted reasoning objects allowed researchers to recover internal secrets—including API keys and passwords—by replaying reasoning blocks across sessions.
Zoom Annotation Bug Could Let Attackers Hijack Any Meeting Client
A critical flaw in Zoom's annotation feature could have allowed any meeting participant to silently take over another attendee's computer. No clicks, no downloads, and no visible warnings were required.
Passkey Attacks Can Now Bypass Phishing-Resistant MFA
Three independent research efforts have demonstrated ways to defeat passkey protections without breaking their underlying cryptography. The findings cast doubt on the widely held belief that passkeys are a near-perfect defence against phishing.
CSS Attacks Can Steal Passwords Across Major Webmail Platforms
New research reveals CSS-based attack techniques that allow content inside an email to escape its message boundary and compromise the webmail interface itself. Gmail, Outlook, Proton Mail, and others are affected.
New CPU Attack Bypasses Spectre v2 Defenses on Intel and AMD
MIT CSAIL researchers have discovered a novel CPU-level attack called INTERRUPT INJECTION that defeats existing Spectre v2 mitigations on Intel and AMD processors. The technique exploits a timing gap between branch-predictor sanitization and kernel execution.
