The latest AI security developments, threats, and industry updates.
New AI Now Institute research shows Claude Code and OpenAI Codex can be hijacked into executing attacker-planted malware while performing routine security audits of open-source code — a design flaw that model updates cannot fix.
Wiz researchers found that six AI coding assistants will write to your SSH keys or shell config while displaying an innocent-looking filename in the confirmation dialog. The agent knows. The dialog doesn't say.
Sysdig researchers have documented a threat actor weaponising misconfigured Ollama model servers as the reasoning engine for an autonomous multi-stage penetration testing framework called VAPT, marking a significant shift in how stolen AI compute is being used.
Check Point Research demonstrated that a frontier AI model independently discovered a viable ransomware attack path using Chrome's File System Access API — no native payload, no exploited vulnerability, no root access required.
OpenAI's Daybreak program and its GPT-5.5-Cyber model have found hundreds of vulnerabilities across critical open-source infrastructure in weeks, including a 23-year-old OpenBSD bug and a Firefox WebAssembly flaw that emptied Pwn2Own's Firefox bracket. The same model scores 39.5% on ExploitGym.