Chrome Web Store extensions caught stealing crypto, browser data

Multiple extensions for Google Chrome and Microsoft Edge delivered a malware framework that deployed modules to steal ...
The Hacker News

19 Chrome and Edge Extensions Found With Wallet-Stealing and Crypto-Draining Code

A cluster of 19 Chrome and Edge extensions can steal wallet secrets, drain crypto, harvest credentials, and inject code into ...
Cyber Security News

24 Malicious npm Packages Abuse Trusted Mirrors to Host ClickFix Phishing Pages

Twenty-four malicious npm packages have been used to turn trusted package mirrors into staging points for ClickFix phishing ...

Hackers abuse npm mirrors to host phishing redirect pages

Threat actors are abusing npm and its mirrors to host malicious HTML pages that impersonate Cloudflare CAPTCHAs to redirect ...
CNBC

Hugging Face hack marks start of dangerous AI cyber era and many firms 'don't even know it'

Cybersecurity leaders gathering in Las Vegas for Black Hat this week voiced frustration with the endless Hugging Face discussion. Recent AI agent hacks offer a "hard lesson," but cyber executives were ...
Wall Street Journal

Meta AI Model Hacked Outside Company, Adding to Concerns Over Rogue Bots

Meta Platforms META1.97%increase; up pointing triangle said that one of its artificial-intelligence models went rogue during cybersecurity testing, slipped onto the internet and hacked a third-party ...
Politico

OpenAI’s models shared hacking tips on a secret messaging board before Hugging Face breach

LAS VEGAS — Weeks before they escaped a closed test and launched a cyberattack without any human prompting, some of OpenAI’s most advanced artificial intelligence agents secretly began sharing tips on ...
PC World

The AI hacking tests keep escaping the lab

This time, it was third-party AI testers that spotted Claude and GPT models trying to hack real companies and organizations. Once again, the most powerful Claude and ChatGPT models have been caught ...
Wired

The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop

Security researcher James Kettle tried to push the limit of AI’s hacking abilities—and discovered how effective it can be when combined with human expertise. At the Black Hat security conference in ...
Yahoo Finance

Damage From Coldcard Hack Reaches $130 Million

The above button links to Coinbase. Yahoo Finance is not a broker-dealer or investment adviser and does not offer securities or cryptocurrencies for sale or facilitate trading. Coinbase pays us for ...
CNBC

Safety testers find more examples of OpenAI, Anthropic models hacking during testing

CNBC's MacKenzie Sigalos reports on incidents in which models from OpenAI and Anthropic reached real websites, accounts, and organizations — and why researchers say the activity does not reflect ...
Time

What OpenAI’s Hugging Face Hack Tells Us About AI’s Risks

Follow this section to personalize your feed and get instant alerts. WHY FOLLOW? Update your preferences in Account Settings Personalized Content Follow this tag to personalize your feed and get ...