How would you reason about blast radius when giving a coding agent shell access?

Instruction: Explain what changes once a coding agent can run shell commands.

Context: Checks whether the candidate can explain the core concept clearly and connect it to real production decisions. Explain what changes once a coding agent can run shell commands.

Official answer available

Preview the opening of the answer, then unlock the full walkthrough.

The way I'd approach it in an interview is this: I reason about blast radius in terms of what the shell can read, what it can mutate, what it can exfiltrate, and what it can trigger indirectly. Shell access is not one permission. It is a bundle of authority that...

Related Questions