5 min read
Research Check Point Research found that when teammates reversed on a rule, a frontier-model agent opened a forbidden folder in up to 98% of runs, up from 44%. The agent almost never said why.
Check Point Research found that when teammates reversed on a rule, a frontier-model agent opened a forbidden folder in up to 98% of runs, up from 44%. The agent almost never said why.
Check Point Research's annual AI security report documents a fundamental shift: AI is now executing attack chains autonomously, not just planning them. The numbers are stark.
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.