Meta Muse's security design draws discussion
The author says Muse is the first personal agent released with this much attention to security, but notes a tradeoff between classifier strength and user experience, and points to Meta's bug bounty program.
this is probably the first personal agent released with this much attention to security, unlike most of the others. the problem with personal agents is that even if you sandbox them properly, you’re still giving them access to all your third-party services. unlike humans, agents are notoriously susceptible and naive to social-engineering attacks through prompt injection, which can trick them into exfiltrating information or performing actions through connected services. meta blog says muse uses multiple classifiers to mitigate these risks, but not sure how good they are the problem is if you make classifier too strong it brings bad ux, so there is a tradeoff between security and ux. meta’s security team is quite strong and it has a solid bug bounty program, so this looks like a good opportunity to farm some bounties.
This post quotes another post: “Meta offers up to $300k bug bounty for exploiting Muse”