> The real key materializes only when the sandbox makes an outbound request to an approved host. If prompt-injected code tries to exfiltrate that placeholder to evil.com? Useless.
That seems clever.
It's a little HTTP proxy that your application can route requests through, and the proxy is what handles adding the API keys or whatnot to the request to the service, rather than your application, something like this for example:
Application -> tokenizer -> Stripe
The secrets for the third party service should in theory then be safe should there be some leak or compromise of the application since it doesn't know the actual secrets itself.
Cool idea!
I cannot remember what the platform was called, let me know if you do.