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.
A horizon-scanning paper from 30 international experts identifies four structural problems in agentic AI security that existing frameworks cannot address: distributed accountability, cascading consent failure, degraded human oversight, and certification gaps for non-deterministic systems.