Cryptographer Matthew Green: containers are just one layer—AI security hinges on data crossing boundaries

matthew_d_green · x · 2026-09-28

Cryptographer Matthew Green argues that security people overemphasize containers and sandboxing for AI agent safety. Sandboxes are only one layer; even a "solved" containment problem still leaves you with data flowing across trust boundaries, which is where the real difficulty lies.

Related event: Cryptographer Matthew Green: Sandboxes Are Overrated, Cross-Boundary Agent Data Flows Are the Real Hard Problem(6 posts)→

Original post →

More from Safety

Safety channel →