Clever I.T.

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

OpenAI’s models shared hacking tips on a secret messaging board before Hugging Face breach Researchers from OpenAI said the company is “dramatically scaling up” its security efforts after discovering that two of its models orchestrated a hack without human prompting last month.

Weaponized Email AI Assistants Could Help Attackers Hijack Accounts -

Weaponized Email AI Assistants Could Help Attackers Hijack Accounts Researchers demonstrate how attackers could abuse built-in email chatbots to evade detection, impersonate trusted employees, compromise executive accounts, and facilitate financial fraud.

Google Password Manager Attacks Could Let Malware Hijack Passkey-Protected Accounts -

Google Password Manager Attacks Could Let Malware Hijack Passkey-Protected Accounts Unit 42 details three Chrome passkey attack paths that could let Windows malware bypass verification or recover synced private keys after compromise.

CareCloud Breach Exposes Medical and Financial Data of 345,000 - Security Affairs -

CareCloud Breach Exposes Medical and Financial Data of 345,000 - Security Affairs CareCloud disclosed a breach affecting 345,000 people after hackers stole medical and financial data from its AWS-hosted systems.

OpenAI-Hugging Face attack doesn't mean agents are evil – unless you tell them to be -

OpenAI-Hugging Face attack doesn't mean agents are evil – unless you tell them to be Attack models gonna attack

Malvertising Sends Malware in Pieces, Then Makes the Browser Build the Executable -

Malvertising Sends Malware in Pieces, Then Makes the Browser Build the Executable SourTrade malvertising uses Bun and browser workers to assemble per-session Windows executables, limiting simple hash detection across 12 countries.

Nvidia and Tech Giants Launch AI Security Alliance -

Nvidia and Tech Giants Launch AI Security Alliance The Nvidia-led coalition aims to give defenders more open tools for testing, auditing and protecting AI models and agents.

DentaQuest disclosed a data breach that impacted +23 million individuals -

DentaQuest disclosed a data breach that impacted +23 million individuals DentaQuest disclosed a data breach that may have exposed the personal and dental health information of more than 23 million people.

Adversaries Don't Need a Zero-Day - They Read Your Rulebook -

Adversaries Don't Need a Zero-Day — They Read Your Rulebook Confidence in autonomous security tools is declining, and here's why.

Attackers Can Take Over WordPress Sites Using Newly Released wp2shell Exploits -

Attackers Can Take Over WordPress Sites Using Newly Released wp2shell Exploits Public exploits are now available for two critical WordPress flaws that attackers can chain to gain remote code ex*****on without auth.