A multi-agent expense system must call a line-of-business API that authorizes actions based on the signed-in employee's identity and group memberships. The orchestrator and tools currently use a single long-lived application secret with broad application permissions, so every agent acts with the same superuser power. Which authentication design best aligns with least privilege for user-scoped actions?
Select an answer to reveal the explanation.
Short Explanation
The correct answer is B. When the API cares who the employee is, agents should call it with that employee's delegated token via OAuth 2.0 on-behalf-of style flows, not a shared superuser app secret. That keeps scopes and group checks real. Stuffing passwords into prompts is a non-starter. Public API keys and no auth at all are worse.
Full Explanation
Option B is correct. Multi-agent security design includes authentication flows such as on-behalf-of, OAuth 2.0, and user impersonation patterns so tools enforce the real user's permissions. Delegated tokens restore least privilege and auditability compared with a single high-privilege application secret used by every agent.
Option A is incorrect because storing or prompting user passwords in agent instructions is insecure, non-compliant, and incompatible with modern identity platforms.
Option C is incorrect because publishing API keys in public repositories exposes the system to abuse and still lacks per-user authorization.
Option D is incorrect because disabling authentication removes access control entirely and is unacceptable for line-of-business expense actions.