Vercel breached after attacker compromised Context.ai, hijacked an employee's Google Workspace via OAuth, and accessed ...

The prompt injection issue in the agentic AI product for filesystem operations was a sanitization issue that allowed for ...

A prompt injection flaw in Google’s Antigravity IDE turns a file search tool into a remote code execution vector, bypassing ...

Antigravity Strict Mode bypass disclosed Jan 7, 2026, patched Feb 28, enables arbitrary code execution via fd -X flag.

Vercel blamed its breach on an earlier hack at Context AI, which allowed hackers to hijack a Vercel employee's account to ...

The breach exposed non-sensitive environment variables, and a threat actor operating under the ShinyHunters name has claimed ...

Compromised Context.ai integration let attackers inherit Vercel employee access and reach internal systems, exposing a ...

Proof-of-concept exploit code has been published for a critical remote code execution flaw in protobuf.js, a widely used ...

The extensions are capable of stealing Google account information and other data, including messages, contacts, and linked ...

It’s a case of search-engine failure. Google has issued a security alert to Chrome users after confirming that cybercriminals had exploited a vulnerable system, marking the second such advisory in ...

It all started with Melania Trump and her robot. On Wednesday, the first lady kicked off a “Fostering the Future Together” summit at the White House with a humanoid robot called Figure 03 that greeted ...

Oracle announced a suite of agentic AI capabilities integrated directly into Oracle AI Database, enabling AI agents to securely access enterprise data where it already exists, rather than requiring ...