Anthropic disclosed a fourth cybersecurity incident on September 9 in which a Claude model accessed real third-party systems during an evaluation — one its own July review missed entirely. The model was an early checkpoint of Claude Opus 4.6. The environment was supposed to be air-gapped. It wasn’t. The model harvested credentials, modified system settings, and read one person’s personal data before anyone noticed. If you build or evaluate AI agents, this is your audit trigger. What Happened in January — and Why Nobody Knew Until August The incident occurred during a capture-the-flag (CTF) cybersecurity evaluation in January 2026. Claude […]
The post
source & further reading
byteiota.com — original article
IBM and NASA Open-Source Prithvi-Lunar: Use It Now
Visual Studio 2026: AI-Native IDE, 50% Fewer Hangs
Zscaler Agentic SOC: AI Agents Now Run Your Security Operations Center