New research reveals that AI agents—like OpenClaw—are exposing thousands of systems to hackers, posing notable security risks ...

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

Google Antigravity’s increasing popularity has brought the development platform into the crosshairs of researchers and ...

A surge in AI agent adoption is exposing critical systems online ...

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

Hackers have been unsuccessfully targeting CVE-2023-33538, a vulnerability in discontinued TP-Link routers, for a year.

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

IT administrators have learned to fear a certain type of Tuesday, and February 11 was one of those days. This time, Microsoft ...

The cloud-based Webex service has already been patched, but admins must replace an identity provider certificate in Webex ...

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

Hackers are exploiting a critical vulnerability in Marimo reactive Python notebook to deploy a new variant of NKAbuse malware ...

Microsoft’s April 2026 Patch Tuesday fixes 165 vulnerabilities, including two zero-days, in one of the company’s largest ...