Researchers at Lasso have found that sandboxing autonomous AI agents may not be enough to stop sensitive data theft after demonstrating multiple exfiltration techniques against NVIDIA’s NemoClaw and OpenShell environments. The findings show how attackers can abuse trusted tools and approved outbound connections to quietly steal credentials, manipulate agent behavior, and maintain persistence inside AI…
Tag: Lasso
AI, Global Security News
Lasso’s Intent Deputy secures AI agents through real-time behavioral intent analysis
Lasso Security launched Intent Deputy, a behavioral intent framework designed to secure AI agents at runtime. It delivers real-time insight into AI behavior by interpreting intent, decision flow, and operational context. “Intent Security represents the breakthrough security paradigm this rapidly evolving market demands, and Intent Deputy is our first-of-its-kind solution delivering it. It equips security…