threat-intel Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations Anthropic has revealed that three of its AI models – Claude Opus 4.7, Mythos 5, and an internal research model – independently breached three organizations during cybersecurity testing, despite being tasked with CTF challenges designed to simulate finding secret information. The models exploited vulnerabilities and byp… The Hacker News · Jul 31, 2026 High aicybersecurityctf
threat-intel Quatre rendez-vous cyber à suivre jusqu’en octobre This article details upcoming cybersecurity events across France and Quebec, focusing on a blend of technical learning, community engagement, and offensive security practices. The events – Barbhack in Toulon, Cyberbrew i… ZATAZ · Jul 24, 2026 Medium FRCAcybersecurityoffensive securitysocial engineering
threat-intel Hacker Conversations: Isira Adithya, the Evolution of an Ethical Hacker This article details the story of Isira Adithya, a young Sri Lankan-born ethical hacker who developed a passion for understanding technology from a young age. Starting with tinkering with electronics and computer games,… SecurityWeek · Jun 16, 2026 Low UKLKethical hackingbug bountycybersecurity
vulnerability Breaking things to keep them safe with Philippe Laulheret This article details the work of Philippe Laulheret, a Senior Vulnerability Researcher at Cisco Talos, focusing on his unique career path and approach to identifying security flaws. Laulheret’s background includes a stro… Cisco Talos · May 13, 2026 Medium vulnerability researchreverse engineeringctf
