Right, we have to see credentials and personal data as different problems. Wirken addresses the first directly and only partially the second. Session scoping keeps injection damage inside one channel's scope so a poisoned email cannot reach into your Telegram credentials. The model still reads the email content during that session, and any prompt injection in that content can still act within what just that session can reach.
The layer that addresses content-level flow is information-flow enforcement above identity. TriOnyx (https://github.com/tri-onyx/tri-onyx) looks at that exact problem: taint and sensitivity tracking, gateway kills on threshold breach.
It complements Wirken. You need identity before you can meaningfully ask what agent A has been exposed to.
On the agent-gets-its-own-machine approach, that is fine as a blast-radius strategy and I have no quarrel with it. It trades isolation between channels for isolation between the agent and the host. If you only have one channel and disposable keys, it works. It stops working as soon as the agent holds something you cannot cheaply rotate, which for most people ends up being their messaging identities.
The layer that addresses content-level flow is information-flow enforcement above identity. TriOnyx (https://github.com/tri-onyx/tri-onyx) looks at that exact problem: taint and sensitivity tracking, gateway kills on threshold breach.
It complements Wirken. You need identity before you can meaningfully ask what agent A has been exposed to.
On the agent-gets-its-own-machine approach, that is fine as a blast-radius strategy and I have no quarrel with it. It trades isolation between channels for isolation between the agent and the host. If you only have one channel and disposable keys, it works. It stops working as soon as the agent holds something you cannot cheaply rotate, which for most people ends up being their messaging identities.