An attacker broke into competitive-intelligence vendor Klue, stole OAuth tokens its customers use to connect to Salesforce ...

A vulnerability chain dubbed AutoJack in Microsoft’s AutoGen Studio interface for prototyping AI agents could let attackers manipulate an agent into executing arbitrary commands on its host system ...

(L-R) Gareth Davies, CPO at Auth0 (Okta) and Tiago Sada, Chief Product Officer, Tools for Humanity speak onstage as Sam Altman and Alex Blania Present Lift Off, a World Event at The Midway SF on April ...

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

Google reportedly patched a flaw in the Vertex AI SDK for Python that could allow attackers to hijack model uploads and ...

Security vendors and their customers have spent considerable time debating where to draw the line between “legitimate” AI agents and “malicious” bots. A 31-day campaign against a major consumer ...

North Korea-linked ScarCruft uses fake Microsoft Account alerts and ZIP files to deliver NarwhalRAT, a Python RAT built for ...

A phishing kit subverting Microsoft’s legitimate authentication flow lets attackers break into accounts without stealing ...

Splunk issued security updates for a critical CVSS 9.8 vulnerability in Splunk Enterprise that allows unauthenticated remote ...

Learn what Claude Code is, how Anthropic’s AI coding agent works, where it excels, its limits, pricing concerns, and who ...

In this article, MIRACL explores how passwordless authentication and zero-knowledge cryptography can help organizations strengthen identity security while reducing friction for users. As cyber threats ...

As threat actors operationalize AI to accelerate attacks, they are also leveraging the wider global interest around AI itself ...