By tricking AI chatbots into ignoring their own rules, attackers are bypassing enterprise security with plain English. Here ...

A high-severity Roundcube Webmail vulnerability patched in May is now being actively exploited in attacks, according to the Canadian Centre for Cyber Security.

Hackers can now weaponize AI coding assistants using nothing more than a booby-trapped license file, turning developer tools into silent spreaders of malicious code. That's according to a new report ...

Prompt injection is the AI era's version of social engineering, and it's already happening in the wild. If you're deploying ...

Hugging Face discloses cyberattack where malicious code hidden in a dataset exploited flaws in its systems, enabling privilege escalation and credential theft The incident was unique in being ...

The ConnectWise ScreenConnect vulnerability, which earlier this year was identified as a potential way for threat actors to perform ViewState code injection attacks, is now being exploited, according ...

Security leaders must adapt large language model controls such as input validation, output filtering and least-privilege access for artificial intelligence systems to prevent prompt injection attacks.

Emily Long is a freelance writer based in Salt Lake City. After graduating from Duke University, she spent several years reporting on the federal workforce for Government Executive, a publication of ...

CISA is alerting federal agencies in the U.S. of hackers exploiting a recently patched ScreenConnect vulnerability that could lead to executing remote code on the server. The agency is warning that ...

ConnectWise disclosed on May 28 that its network was breached in an attack that targeted ScreenConnect customers. The software company, which makes remote monitoring and management (RMM) tools like ...