Security researchers warn that Anthropic’s Claude in Chrome extension can be abused by malicious extensions that exploit ...

OpenAI’s Codex Chrome extension pushes the coding agent into signed-in browser work, making it more useful for real tasks while raising new questions about access, approvals, and agentic AI risk.

Anthropic's Mythos AI is being called powerful enough to uncover hidden cyber threats, but Mozilla's latest report shows how ...

Mythos helped Mozilla Firefox discover 271 critical bugs. The result has sharpened questions about the tool's power and risk.

The vm2 sandbox component of the open-source JavaScript runtime environment Node.js is vulnerable with certain settings.

CVE-2026-44009 (CVSS score: 9.8) - A vulnerability that allows sandbox escape via a null proto exception and permits an ...

Mythos’s ability to autonomously exploit flaws challenges the notion of ‘secure by default’. , Technology & Science, Times ...

Thirteen critical vulnerabilities have been found in the vm2 JavaScript sandbox package that could allow an attacker’s code ...

A critical vulnerability in the popular Node.js sandboxing library vm2 allows escaping the sandbox and executing arbitrary ...

Emergency patches out now for those managing the millions of domains assumed to be affected This CVSS 10.0 RCE vuln has been ...

A North Korean APT has crafted malicious software packages to appeal to AI coding agents, while ‘slopsquatting’ shows the ...

VectorCertain LLC today announced new validation results demonstrating that its SecureAgent platform successfully detected and prevented 100% of AI sandbox escape attempts across 831 adversarial ...