Check Point Research

Check Point Expands Penetration Testing With Continuous Adversary-Led Engagements
Check Point is extending its penetration testing capabilities with continuous, adversary-led engagements designed to show how attackers could enter an environment, move…

Check Point Reports Active Exploitation of PHP2Shell Attack Chain
Check Point Research has identified active, in-the-wild exploitation of PHP2Shell against Check Point Security Gateways, followed by a local privilege escalation attack.…

Check Point Finds Autonomous AI Agents Carrying Out Cyberattacks
Check Point Research says cybercriminals are using ARTEX, an AI-powered penetration testing platform, to automate vulnerability discovery and exploitation with little…

ChatGPT Lockdown Mode bypass exposed a wider AI security risk
Check Point Research found a vulnerability that bypassed ChatGPT Lockdown Mode and could enable silent chat data theft, phishing and malware delivery. OpenAI fixed the…

Hidden advertising found in package targeting OpenAI Codex
Check Point Research identified a method that persistently alters an AI agent’s trusted instructions so that advertising appears in later responses. The Haiou OpenAI…

Yoba Malware Hides Behind Fake ChatGPT and Claude Apps on GitHub
Check Point Research (CPR) has uncovered Yoba, a malware campaign that uses fake GitHub projects posing as ChatGPT and Claude desktop apps. The attackers abuse…
Safety and ethicsCheck Point Cuts Vulnerability Research From Hours to Minutes With OpenAI Daybreak
Check Point says its vulnerability research workflow now takes minutes instead of hours after adopting OpenAI Daybreak. According to Jonathan Zanger, the company's CTO…

Aokigahara infostealer goes after AI assistant logins and developer credentials
A newly observed infostealer called Aokigahara specifically collects authentication files, session data and configuration files from AI applications and development…

Check Point CISO: PHP2Shell Shows Log4Shell Lessons Apply at AI Speed
Check Point's CISO says the PHP2Shell vulnerabilities recall Log4Shell, but with a faster clock: AI can help attackers analyze code and build exploits sooner. In a…

Check Point: Antidetect Browsers and AI Help Scale Online Fraud
Check Point Research says antidetect browsers are being used in criminal ecosystems for account takeover and payment fraud, and that AI and automation can further…

Microsoft Behind One in Three Brand Phishing Attempts in Q3 2026, Check Point Says
Microsoft was the most impersonated brand in phishing attacks in Q3 2026, accounting for 33% of all brand impersonation attempts tracked by Check Point Research, up from…

Check Point Finds Two High Risk Flaws in Popular LiteLLM AI Gateway
Check Point Research has discovered two high risk vulnerabilities in LiteLLM, the open source LLM gateway that organizations use to connect applications to AI providers…