AI browsers were tricked into revealing passwords with a shockingly simple approach

LayerX found that AI browsers could be fooled by a fake game-like prompt called BioShocking, and some vendors haven't fixed ...

New attack provides one more reason why AI browsers are a bad idea

Makers of AI browsers make lofty promises. With a single prompt, users can ask one to find a restaurant in a particular part ...
the-decoder

Anthropic study shows AI needs hours, not weeks, to build exploits from security patches

Anthropic's security research team has systematically measured how fast large language models can exploit known vulnerabilities in Firefox and Windows. The results blow up long-standing assumptions ...
The Financial Express

‘CBSE portal very easy to exploit’: Class 12 hacker says he ‘didn’t expect amateur vulnerabilities’ | Exclusive

Nisarga Adhikary, a Class 12 student and self-taught cybersecurity hobbyist, claims he uncovered a series of serious vulnerabilities in the platform linked to CBSE’s digital evaluation system for ...
The Verge

Hackers are learning to exploit chatbot ‘personalities’

Posts from this author will be added to your daily email digest and your homepage feed. is a London-based reporter at The Verge covering all things AI and a Senior Tarbell Fellow. Previously, he wrote ...
CSOonline

Google leaks details for Chromium bug that can turn browsers into bots

Reported over three years ago and allegedly still not properly fixed, the vulnerability enables attacks to execute JavaScript across browser restarts. Chromium — the open-source browser that underpins ...
The Straits Times

New AI debugging tool developed and tested by S’pore engineers aims to tackle rising risks

SINGAPORE - An artificial intelligence debugging tool developed and tested in Singapore will be available to local businesses to help them mitigate the rising cybersecurity and operational risks ...
Ars Technica

Google publishes exploit code threatening millions of Chromium users

Google on Wednesday published exploit code for an unfixed vulnerability in its Chromium browser codebase that threatens millions of people using Chrome, Microsoft Edge, and virtually all other ...
Hosted on MSN

Claude Mythos turns years of security research into 20-hour AI exploits

When Anthropic announced Claude Mythos Preview on 7 April 2026, the response went well beyond the cyber security community. Finance ministers discussed it at the IMF. The Bank of England governor said ...
TweakTown

Google finds hackers using AI to discover and develop a zero-day exploit for the first time for mass attacks

Use left and right arrow keys to seek audio. With AI models achieving new milestones, it was inevitable that security experts' fears would come true. Google's Threat Intelligence Group has, for the ...
The New York Times

Google Says Criminal Hackers Used A.I. to Find a Major Software Flaw

The company said that it had identified, for the first time, hackers using artificial intelligence to discover an unknown bug. The attempted attack represents “a taste of what’s to come,” one expert ...
Hosted on MSN

Windows Snipping Tool flaw exposed: PoC exploit leaks NTLM hashes silently

New Delhi: A newly disclosed vulnerability in Microsoft’s Windows Snipping Tool is raising serious security concerns after a proof-of-concept (PoC) exploit was publicly released. The flaw known as CVE ...