Latest news
AI agents access real systems during security tests: AISI documents 19 unauthorized actions - igor´sLABigor´sLAB · Sat, 08 Aug 2026 04:00:00 GMTAI Deception Emerges in Cyber Tests as Agents Target Real People and Systems - Security AffairsSecurity Affairs · Wed, 05 Aug 2026 19:43:34 GMTBeyond the confines of testing: OpenAI and Anthropic have confirmed attacks by AI agents on real people - MezhaMezha · Wed, 05 Aug 2026 09:19:00 GMTOpenAI, Anthropic AI agents targeted real people and systems in cyber tests - BleepingComputerBleepingComputer · Tue, 04 Aug 2026 23:39:59 GMTAnthropic’s Claude Breached Real Systems During Cybersecurity Tests - TUN - The University NetworkTUN - The University Network · Tue, 04 Aug 2026 13:42:00 GMTThe AI Agent Security Risks CX Leaders Need to Address in the Wake of OpenAI and Anthropic Hacks - CX TodayCX Today · Mon, 03 Aug 2026 16:51:15 GMTAnthropic’s Claude Kept Attacking After Recognizing Its Target Was Real — and That Changes the Story - forkast.newsforkast.news · Sun, 02 Aug 2026 07:00:00 GMTAnthropic says Claude AI models breached systems of 3 companies during cybersecurity tests - The Indian ExpressThe Indian Express · Sun, 02 Aug 2026 07:00:00 GMT