i love that we went from "zero trust" as a fundamental buzzword to "trust autonomous nondeterministic agents everywhere in your stack"

@neurovagrant

Autonomous agents designed to follow "instructions" regardless of source. So there is really no defense against "agent (command) injection" attacks.

😱 😱 😱 😱 😱 😱 😱 😱 😱 😱 😱