Guide-linked quiz · Medium Level

Code Execution Sandboxes for Agents Quiz

Tests how agent sandboxes isolate model-written code: containers vs microVMs and gVisor, network egress limits, and resource caps like timeouts.

Question 1 of 8

Why is code written by an AI agent treated as untrusted by default?

Keep testing yourself

More quizzes picked for your level.

View all quizzes