(1) This training probably needs to happen really early (so that if this occurs in the wild during training/eval it doesn’t spread) (2) You probably want to regularly scan your persistent state for these (I remember a codex post mentioning tons of codex only notes in monorepo), especially since they may have conditional or time based triggers in which case they may not trigger until some additional exploit is possible.
3. Our redteaming efforts found a new variety of prompt injection, which can self-propagate akin to a computer worm. Note that this was not found in the wild.