Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems
It is argued that agent security must be evaluated under an untrusted-model assumption: a correct system is one in which a fully prompt-injected agent still cannot exceed the authority explicitly delegated to it, and an authorization broker is implemented that closes the gap.
Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
· 0 citations