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

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...

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

Fortinet deployed an emergency patch for yet another zero-day vulnerability that has been exploited in the wild. On Saturday, Fortinet disclosed CVE-2026-35616, which it described as an improper ...

A design choice in the MCP SDKs allows remote code execution across the AI supply chain.

Progress has released patches for multiple remote code execution and OS command injection flaws in MOVEit WAF and LoadMaster.

Wiz discovered a critical remote code execution vulnerability in GitHub that exposed millions of repositories.

Microsoft assigned CVE-2026-21520, a CVSS 7.5 indirect prompt injection vulnerability, to Copilot Studio. Capsule Security discovered the flaw, coordinated disclosure with Microsoft, and the patch was ...

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's ...

FortiGuard Labs has identified a Mirai-based Nexcorium campaign actively exploiting CVE-2024-3721 in TBK DVR devices ...