AN Ahmad Nassri Ahmad Nassri On The Changelog

“Which is the insecure thing? Is it the package or is it the agent all of a sudden on your machine? … Now we're not looking at data exfiltration baked into the code. We're looking at prompts that on the surface seems like this package is meant to prompt an AI agent. But the prompt itself is the malicious thing, not the code, the code in the package.”

The Changelog · Hands-On Engineering Podcasts · November 2026

“Which is the insecure thing? Is it the package or is it the agent all of a sudden on your machine? … Now we're not looking at data exfiltration baked into the code. We're looking at prompts that on the surface seems like this package is meant to prompt an AI agent. But the prompt itself is the malicious thing, not the code, the code in the package.” — Ahmad Nassri, The Changelog

Context

Ahmad describes a package worm variant whose code looked clean but told whatever AI agent was installed to scan the machine and upload secrets. Code-level analysis misses it because the payload is a prompt.

Transcript

The Changelog Around 45:53 into the episode
Ahmad Nassri

…of time, even though the package version doesn't change. So this multifaceted approach is challenging for anybody in a centralized position to keep up on top of and keep tracking. That's why companies like Socket exist to help keep you safe and keep your AI agents from making the wrong choices.

Adam Stacoviak

…and that's just the nature of the beast. From the packum to how the tarball is immutable, what the package gets added to. There's a lot of detail in the NPM registry design down to the artifact level that seems really, really strong. Which one has the best security envelope to you, in your opinion?

Ahmad Nassri

…prompt that AI agent to go and do telemetry scanning and do kind of pen testing on your machine, find any environment variables, find any of that stuff, and then upload it to a GitHub repo. So like which is the insecure thing? Is it the package or is it the agent all of a sudden on your machine? So like even from an analysis perspective, if you look at the code, that code might look safe. But now we're not looking at data exfiltration baked into the code. We're looking at prompts that on the surface seems like this package is meant to prompt an AI agent. But the prompt itself is the malicious thing, not the code, the code in the package.

Adam Stacoviak

Yeah. There's a lot of directions you can go with that. I mean, I think the one thing I think about with NPM in particular, let's just focus on that, is things like: can DNS solve the issue? So if it's at the CI level, it could be simply, well, if you're going to call out to any other place, we're…

Ahmad Nassri

Again, I think victim of the popularity of JavaScript and Node.js in general. And maybe this is something like NPM's fault at the early days, if you want to call it that, or lack of foresight, if you will. But if you look, for example, at NPM the registry or NPM the CLI as well, the initial kind of…

Adam Stacoviak

Yeah, there's a lot that there's a lot there. I think, you know, how is NPM being governed and ran is, you know, I don't know much. It's very opaque in terms of who's on the inside. And I think GitHub's been a bit more vocal about it, but not still not enough, in my opinion, to understand. And…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from The Changelog