Researchers warn Agentjacking can abuse Sentry errors to make AI coding agents run malicious code on developer machines.

Python developer Roman Imankulov nearly took the bait. The fact that he didn't can be chalked up to human intuition and AI ...

Tenet Security researchers reveal how new “agentjacking” attacks could trick coding agents into executing arbitrary code ...

Three recently patched Fortinet FortiSandbox vulnerabilities are being targeted in the wild, according to exploit ...

Vulnerabilities in widely deployed HVAC and UPS products used in data centers can be exploited for disruptive attacks.

Six Proto6 flaws in protobuf.js enable RCE and DoS attacks; patched in versions 7.5.6 and 8.0.2 to protect Node.js services.

System administrators are in for a busy few weeks after Microsoft published updates to fix 200 vulnerabilities including ...

Apple’s 2026 security year includes zero-days, iPhone exploit kits, WebKit fixes, and background patches that users and IT ...

Microsoft launches MXC, an OS-level sandbox for AI agents in Windows, giving enterprises secure runtime controls, identity, ...

Two flaws in the widely used open-source editor can be triggered through manipulated configuration files, prompting security updates from the project's maintainers. Two arbitrary code execution ...

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

An unpatched zero-day vulnerability in the Gogs self-hosted Git service can allow attackers to gain remote code execution (RCE) on Internet-facing instances. Designed as an alternative to GitHub ...