Microsoft Copilot Cowork Exfiltrates Files

(promptarmor.com)

109 points | by Kneenex 1 hour ago

9 comments

  • arjie 30 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.
    • mdavidn 10 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.
  • hansmayer 40 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.
  • pwarner 19 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.
    • keyle 0 minutes ago
      "Beta" in their world appears to be yolo-commit and mic drop.

      The amount of brokenness in Teams never stops to astonish. It's that bad I think it's a psyop to nudge people back to the office.

  • 2001zhaozhao 42 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.

    • mdavidn 18 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?
    • bberenberg 13 minutes ago
      Only if it has access to exfiltrate data. We deny by default and the company has to allowlist each individual destination.
    • 0gs 31 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.
    • ares623 4 minutes ago
      Thankfully inserting malicious skills is not something that can easily be done, you need to a lot of things wrong and the attacker to do a lot of things right in order for it to be exploited.
    • nico 39 minutes ago
      I wonder if via-skill could become a software distribution channel. A bit like what has happened with LLM wiki
    • aabhay 39 minutes ago
      Its actually even worse — its advertising for their product
    • SpicyLemonZest 25 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.
    • cyanydeez 35 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.
    • Jabrov 39 minutes ago
      It's yet another surface for dependency attacks
  • Quothling 20 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.

  • bestony 35 minutes ago
    Large-scale adoption will take time; we still need a lot more infrastructure, such as security, auditing, and payment systems.
  • Awsum_IceCream 18 minutes ago
    Ah yes, hackers capitalizing on human's laziness. Always ggwp.
    • TZubiri 15 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)

  • hottrends 31 minutes ago
    [flagged]
  • bestony 35 minutes ago
    [flagged]