Couldn't the blueprint exfiltrate incoming data to an external location for example?

Blueprints shouldn't (if I know anything about Kenton) have access to the Internet/external locations without you granting it permission to.

The blueprint is just code, it does not include data or capabilities.

It's, I suppose, possible that the agent added secrets to the code itself. Not, like, API keys -- the agent never sees those. But it could have extracted sensitive info and put it into code, perhaps?

We can implement restrictions on exporting blueprints from workspaces that have seen sensitive secrets, though this might be more annoying than useful. It's a tricky balance.