Why securing AI agents at runtime is essential as attackers find new ways to exploit generative orchestration.

Just yesterday, we noted the growing threat of ransomware. Now, Jamf Threat Labs is warning that North Korean threat actors ...

A set of newly disclosed critical vulnerabilities in Fortinet products is raising serious cybersecurity concerns, with national CERT ...

Vulnerabilities in Anthropic MCP server could be exploited via prompt injections to execute arbitrary code and read/delete arbitrary files.

A flaw in the binary-parser npm package before version 2.3.0 lets attackers execute arbitrary JavaScript via unsanitized parser input.

Researchers found the popular model context protocol (MCP) servers, which are integral components of AI services, carry ...

Three vulnerabilities in Anthropic’s MCP Git server allow prompt injection attacks that can read or delete files and, in some ...

Anthropic has fixed three bugs in its official Git MCP server that researchers say can be chained with other MCP tools to ...

Anthropic’s official Git MCP server hit by chained flaws that enable file access and code execution - SiliconANGLE ...

The patched issues span core standard library components including archive/zip and net/http, as well as security-sensitive ...

Overview On January 14, NSFOCUS CERT detected that Microsoft released the January Security Update patch, which fixed 112 security issues involving widely used products such as Windows, Microsoft ...

Among them is a zero-day vulnerability in Desktop Window Manager (DWM) designated as CVE-2026-20805 (CVSS score: 5.5), which ...