OpenAI hacked RubyGems, PyPI typoquats contain prompt injection, and new Mac malware

So late last week, I was heading back from Europe and in the absolute AppSec community, somebody shared a URL and said, curious what you think about this.

And I'll drop it in the chat, but essentially this is new research that has come out about the gem stuffer campaign in Ruby gems.

So let me see here.

I can click, click.

Here's the research if you haven't seen it.

The TLDR is there was a big attack on RubyGems back in May.

It was unattributed at the time.

It was very spammy.

These researchers are alleging that this campaign was done by rogue open AI agents.

And while we don't I guess categorically know if that's true.

I think it also wouldn't surprise us.

So they cited three main reasons that they think an open AI agent swarm was responsible for the incident.

First, they said the packages are clearly LLM authored.

I'm not sure that I agree that that's evidence that it was open AI agents, but sure.

The second is they're saying the agent's self-identified as being from OpenAI.

Okay, that's stronger evidence.

Many of the packages uploaded contain an OAI in their name.

Several have that as their author.

One lists something similar as an email contact.

And then the third reason that they're attributing this to an OpenAI swarm is they're saying it's behaving similarly, very extremely similarly to a German Wiki agents incident that they found earlier in the year where agents accessed 49 of the same files as Wiki agents and OpenAI did confirm that that was their attack.

So before we talk about the part B of this, that is hot news that just came out like an hour ago, Paul, what's your reactions on this Ruby hack disclosure?

Yeah, well, I mean, I've been there since day one.

We've been identifying this stuff and pulling it into OSM.

And so I saw the original, I was like right on it when the original 150 were found in May, the original batch.

And then there was a second wave of about 20, roughly 2,200.