Indirect prompt injection attacks are now draining cryptocurrency from AI agents in production. Zscaler ThreatLabz documented ...

New TELEPUZ malware spreads through ClickFix, then steals browser cookies, logs keystrokes, runs commands, and installs itself as a Windows service.

Claude for Chrome v1.0.80 still accepts forged clicks from other extensions, triggering Gmail, Docs, and Calendar tasks ...

An advanced threat actor is abusing the update mechanism for the ViPNet private networking product suite to target Russian ...

Market research company Klue has confirmed that a credential dating back to 2022, which was part of a limited pilot, was used by hackers earlier this month to steal reams of data from its corporate ...

AI browsers can be convenient, but they also come with security risks.

The Jscrambler client-side web security company disclosed that a threat actor published a malicious version of its npm ...

Consumers may no longer have to wait to find out the details of Apple’s iPhone 18 Pro. Photos of the phone were exposed in a data leak from Tata Electronics, one of the tech company’s manufacturing ...

Prompt injections, the malicious commands attackers embed into content to entice LLMs to follow them, have been attackers’ go ...

Market research provider Klue, which was hacked earlier this month in a breach that allowed cybercriminals to steal reams of data belonging to several of its customers, said that it is communicating ...

LastPass, a password manager maker, is informing customers of a recent security breach at third-party market intelligence platform Klue, and how it impacts its customers, according to a recent blog ...

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are inherently unable to distinguish between legitimate instructions provided by ...