What are they used for? And just kind of bring the listeners into that.

Yeah, no, absolutely.

You know, over the past year, we audited some of the frameworks that the industry is building its agents or AI agents on.

And these are LandChain, LandGraph, Microsoft's agent framework, Google's, you know, ADK, Cloudflare's code mode, Crew.ai. And with these frameworks are used when you as a developer would want to write your own agent, right? So you need to build it on top of something.

We've seen a lot of AI agent exploitation in the last couple of years, lots of prompt injections, trying to persuade the agent to do something else than it intended.

And then we've seen a lot of kind of topical tool abuses.

where you find a vulnerable tool, a specific misconfigured or something that can be injected into, and then you use that tool to gain something as an attacker.

Who would go after