4 days ago · Hackers can trick OpenAI Atlas via prompt injection, treating malicious instructions disguised as URLs in the omnibox as trusted commands.

1 day ago · The vulnerability works on Google Chrome and all web browsers that run on Chromium, which includes Microsoft Edge, Brave, Opera, Vivaldi, Arc Browser, Dia Browser, …

Oct 23, 2025 · For instance, the ChatGPT agent cannot run code in the browser, download files, or install extensions, and it cannot access other apps on the device. However, these types of …

4 days ago · Researchers expose Atlas browser flaw letting malicious URLs trigger AI actions and redirect users.

9 hours ago · In these attacks, the attackers have been found to leverage vulnerable Windows WSUS servers to run a Base64-encoded PowerShell commands, and exfiltrate the results to a …

23 hours ago · “Brash” flaw in Chromium’s Blink engine lets attackers crash browsers instantly via a single malicious URL, researcher Jose Pino revealed.

Sep 22, 2025 · Explore emerging attack methods, evolving AI-driven threats, supply chain risks, and strategies to strengthen defenses and stay ahead of cyber risks.

Sep 9, 2025 · LunaLock, a new ransomware gang, introduced a unique cyber extortion technique, threatening to turn stolen art into AI training data.

Aug 8, 2025 · Two different firms have tested the newly released GPT-5, and both find its security sadly lacking. After fell to a jailbreak in two days, GPT-5 fell in 24 hours to the same …

Aug 20, 2025 · PromptFix exploits Comet AI browser via fake CAPTCHA, auto-filling credit cards and enabling phishing scams.