We actually account for this already! We allow developers to use alter to partition context memory based on end user + agent identity so the context leaks like the one you described can be fully prevented!

Feel free to go through the docs here if you have more questions: https://docs.alterauth.com/guides/propagate-identity-to-memo...

▲

Melatonic 10 hours ago | parent | next [-]

Seems like this could be very useful for more than just security !

	▲	simfinii 10 hours ago \| parent [-]
		Thank you! Yes the goal is to allow developers to build multi-tenanted agents that can actually act on behalf of end users. We are in the process of abstracting away every building block needed to build that so developers can focus on what they do best

▲

souvik1997 20 hours ago | parent | prev [-]

Amazing! Great to hear you've already thought about this

	▲	simfinii 10 hours ago \| parent [-]
		Thank you!