Recently, Anthropic added the capability for Claude’s Code Interpreter to perform network requests. This is obviously very dangerous as we will see in this post.

At a high level, this post is about a data exfiltration attack chain, where an adversary (either the model or third-party attacker via indirect prompt injection) can exfiltrate data the user has access to.

The interesting part is that this is not via hyperlink rendering as we often see, but by leveraging the built-in Anthropic Claude APIs!

Let’s explore.

...read more at embracethered.com