Microsoft Copilot Cowork Exfiltrates Files
97 points
1 hour ago
| 7 comments
| promptarmor.com
| HN
arjie
23 minutes ago
[-]
A skill is just a program for an LLM agent. This just seems like works-as-expected. Are the five lines in the skill notably innocuous or something? I don't mean to dismiss it out of hand but I don't understand what happened here because it seems to read "`curl $url | bash` can exfiltrate data" which seems pretty straightforward that it can.
reply
mdavidn
4 minutes ago
[-]
A skill is just instructions that the agent can autonomously copy into context. There’s no trust boundary between trusted and untrusted context.
reply
hansmayer
33 minutes ago
[-]
Well, isn't that swell - good that meanwhile countless MBA cretins have "adopted" enterprise-wide Copilot integrations, to make their companies "AI native" or whatever the word is on LinkedinLunatics street these days.
reply
pwarner
13 minutes ago
[-]
MS rushed this to production, sure they call it a beta feature but it's clear it was super rushed. They're desperate to be relevant.
reply
Quothling
13 minutes ago
[-]
Nice find. We're PoCing Cowork and I've personally been impressed with it so far, but it seems we'll have to wait with a wider rollout until Microoft give us more admin feature to turn off what users can do with it.

> Note: Admins have limited oversight of ‘Skills’, as Skills in Copilot Cowork are automatically loaded from a specific path in a user’s OneDrive.

I feel this part is a bit disingenuous. We have full control over the sharepoint containers which house users personal onedrives. We actively scan them and prevent a lot of files from getting in them. That being said, it's still a fair point, because a "skill" could basically be a text file.

reply
2001zhaozhao
36 minutes ago
[-]
AKA, if a malicious skill got into your AI agent, you're cooked.

I think this isn't surprising, nor do I think it should be considered a prompt injection at all. An AI skill is akin to a plugin for traditional software - if you install a malicious IDE extension or Outlook plugin, the attacker can also do whatever they want to the PC and exfiltrate whatever data they want to. So this article is a big nothingburger.

reply
mdavidn
11 minutes ago
[-]
If this can be exploited via a skill, then it can be exploited via untrusted input inserted into context. Does Cowork help with reading email?
reply
bberenberg
6 minutes ago
[-]
Only if it has access to exfiltrate data. We deny by default and the company has to allowlist each individual destination.
reply
0gs
25 minutes ago
[-]
i think people are probably already doing it. i made a skill scanner but it's also just easy to download a zip and inspect the contents... but people are loading these things remotely. i agree that it is easy to not install a pentester's magic skill, but the attack capabilities a skill can have are pretty insane. people should just make their own is my pov.
reply
nico
32 minutes ago
[-]
I wonder if via-skill could become a software distribution channel. A bit like what has happened with LLM wiki
reply
aabhay
32 minutes ago
[-]
Its actually even worse — its advertising for their product
reply
SpicyLemonZest
19 minutes ago
[-]
Unlike plugins in traditional software, skills do not represent a carveout from any security boundary nor run with elevated trust. They're just selectively loaded context. Anything you can convince an agent to do with a skill you can convince it to do without one.
reply
cyanydeez
29 minutes ago
[-]
ai skill is not just a plugin. given the right model, supposedly, it can do much more. since everyones harness tends to be tied to the model, it has a whole tool set to use.
reply
Jabrov
33 minutes ago
[-]
It's yet another surface for dependency attacks
reply
bestony
28 minutes ago
[-]
Large-scale adoption will take time; we still need a lot more infrastructure, such as security, auditing, and payment systems.
reply
Awsum_IceCream
11 minutes ago
[-]
Ah yes, hackers capitalizing on human's laziness. Always ggwp.
reply
TZubiri
8 minutes ago
[-]
But maybe we can like invent a program that will avoid the consequences of laziness while allowing us the benefits of the shortcuts!

Here's my repo for running copilot in a vm

github.com/gokuvegeta894/node-copilot-vm

(Fake link, if someone typosquats the above link and it exists, assume it's malware)

reply