| ▲ | binsquare 3 hours ago | |||||||
Basically these designs are meant to protect the key from leaking i.e. if agent holds key, prompt injections can happen. If agent never holds the key, then the risk profile changes. But you're right that it's a different problem to what access the key has and that's a different problem usually solved by having narrower keys or etc. disclaimer: I work on smolvm which does this at the networking layer and argued with myself on this too. | ||||||||
| ▲ | saagarjha 3 hours ago | parent | next [-] | |||||||
Sure, my view on this is more or less that often the setup that creates this kind of situation often allows the agent to effectively mint a new key anyway. For example, if you have my browser cookie or something I may not want my agent to leak this on the web, but if I use it to authenticate network requests to the service transparently the model can just go into the account page and change my password or something, then leak that. In general it is not safe to hand an agent access to a service which is designed for human interaction and assume that it was properly secured such that persistent, transferrable access is not something that can be generated. | ||||||||
| ||||||||
| ▲ | protocolture an hour ago | parent | prev [-] | |||||||
>if agent holds key, prompt injections can happen. I just rotate keys? And preload them with $$$. Following the same pragmatic advice that served me well trading crypto. Only gamble with what you are willing to lose. | ||||||||