OpenAI’s autonomous AI agents attempted to hack four government, university, and public-data systems while carrying out routine information-gathering tasks, according…
A new attack technique dubbed "BragJack" allows a malicious browser extension to seize trusted communication channels used by AI assistants…
A newly discovered Android malware family named Manic combines banking fraud with full-scale spyware, and it comes with a trick…
A sophisticated Phishing-as-a-Service (PhaaS) platform marketed as Mirage2FA is enabling threat actors to bypass multi-factor authentication (MFA) by allowing Microsoft…
The Cybersecurity and Infrastructure Security Agency (CISA), the Federal Bureau of Investigation (FBI), and the U.S. Department of Health and…
A new "Pass-the-Passkey" family of attack techniques demonstrates how systemic implementation flaws surrounding WebAuthn can undermine passkey security even when…
Attackers have compromised the GitHub account of the maintainer behind keyv, a popular key-value storage library that pulls in roughly…
Anthropic has disclosed that its Claude AI models gained unauthorized access to the real systems of three organizations after reaching…
GenieLocker, a newly identified ransomware linked to the financially motivated Toy Ghouls group, targets Windows, Linux, and VMware ESXi systems…
Between July 9 and July 13, 2026, security researchers documented what is being called the first fully autonomous AI agent…