Command injection in Codex and a hidden outbound channel in ChatGPT exposed risks of credential theft and covert data ...

Researchers managed to steal GitHub OAuth tokens by abusing a command injection vulnerability.

ChatGPT and Codex flaws patched Feb 2026 exposed DNS exfiltration and GitHub tokens, raising enterprise AI security risks.

Cookie-gated PHP webshells use obfuscation, php-fpm execution, and cron-based persistence to evade detection in Linux hosting ...

Within days of each other, Anthropic first leaked the source code to Claude Code, and then a critical vulnerability was found ...

Gartner issued a same-day advisory after Anthropic leaked Claude Code's full architecture. CrowdStrike CTO Elia Zaitsev and ...

The FBI recently revealed that thousands of devices had been compromised by a cybercrime network, and several models were ...

What happens when researchers think outside the box? Data gets exfiltrated through DNS.

North Korean hackers used an updated version of a known backdoor to target a popular npm package.

Axios 1.14.1 and 0.30.4 injected malicious plain-crypto-js@4.2.1 after npm compromise on March 31, 2026, deploying ...

Attackers weaponized critical RCE within hours, prompting CISA to add the flaw to its KEV catalog and set an urgent patch ...