I like that this feels driven by a coherent design philosophy. and the emphasis on AI security is very timely as AI-generated code becomes more common
Show HN: Jo – AI-native language to catch prompt injection at compile-time
11–15 of 15 posts
Re: Show HN: Jo – AI-native language to catch prompt injection at compile-time
#12the capabilities design is really cool, however to protect against prompt injection to unauthorized db access, couldn't we just use api only agent or db features like pg RLS
Re: Show HN: Jo – AI-native language to catch prompt injection at compile-time
#13the capabilities design is really cool, however to protect against prompt injection to unauthorized db access, couldn't we just use api only agent or db features like pg RLS
yeah, not really, actually. in my opinion, they may work, but with tradeoffs
api wrappers are safe, but they kill flexibility of AI agent and will have massive maintenance bottleneck
db-level security is a great runtime boundary, but it is completely disconnected from application business logic
Re: Show HN: Jo – AI-native language to catch prompt injection at compile-time
#14[flagged]
Re: Show HN: Jo – AI-native language to catch prompt injection at compile-time
#15Nicely done. This isn't a criticism, but i wonder if a well designed system needs prompt injection guards at all. Provided all security happens outside of the models and models only have access to data and resources that are scoped to the user. I guess model security is exactly the same as employee security, least privilege, sand boxes, etc