← Concept Index

Agent & LLM security

Tool & permission scoping

Also called: least privilege, what the agent can touch

DEFINITION

Deliberately limiting which tools an agent has and what each can access — read-only where possible, one mailbox not all of them, no ability to delete — so a mistake or injection has a small blast radius.

WHY IT MATTERS

It's the most effective agent safeguard because it doesn't rely on the model behaving. Least privilege caps the worst case regardless of what the model is tricked into trying.

COMMONLY CONFUSED WITH

Trusting the model less in the prompt. Scoping is enforced outside the model, so it holds even when the prompt defence fails.

SOURCES

First-pass citations, limited to primary sources; a reviewer will broaden and verify these before this entry leaves draft.