Hacker Newsnew | past | comments | ask | show | jobs | submit | throwingSE's commentslogin

jai is doing the right thing for its threat model. The credential layer is a different surface though ... an agent with a broad API token can call initiate_payment or update_vendor_bank on a remote production system and the filesystem sandbox can't help.

Applying the same principle as jai for remote boundaries, we can scope API authority to the task


Thank you for the advice.

May I ask how you made the shift? Did you do it in the same company? Same industry?

Did you need to do something else aside to make your resume more appealing for those roles?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: