AI agent runs amok in Fedora and elsewhere

(lwn.net)

131 points | by tanelpoder 2 hours ago

12 comments

  • jrochkind1 16 minutes ago
    The worst part:

    > In addition, Williamson said that Giovannini (or his agent) had submitted patches that were incorrect and then "replied to objections with LLM-generated justifications that eventually overwhelmed the maintainer into merging the fix"

  • 12_throw_away 1 hour ago
    In their suspicious message [1] claiming to have been hacked, the user and/or agent says

    > To help identify accounts and actions that have been directly verified by me, I will use the term “NATCIOS” to indicate anything I have personally verified.

    Does anyone have any idea what "NATCIOS" means here? I cannot find this term anywhere on the internet. (Honestly, that sentence is really weird. I almost wonder whether this is someone experiencing a health episode?)

    [1] https://lwn.net/ml/all/AS8PR08MB6055AE3054B34F6A567AC95BCF08...

    • ndiddy 29 minutes ago
      The reply to that message notes that the email doesn't read like previous emails he's sent, and the Github account mentioned was created an hour prior to the email being sent. I think it's at least somewhat feasible that it's still the LLM writing, and the acronym is just something it made up.
      • hn773746483 0 minutes ago
        and the poor Fedora teams will continue to assume good faith and continue to engage with this person... all because, what, they were active on a bug tracker for a few months 5 years ago?

        They won't put their foot down until the AI starts spewing hate speech, probably.

    • Terr_ 50 minutes ago
      Because I'm probably not the only one thinking it, here are anagrams [0] for your Setec Astronomy needs.

      [0] https://wordsmith.org/anagram/anagram.cgi?anagram=NATCIOS&t=...

    • no-name-here 38 minutes ago
      The senders name is Nathan - maybe NAThan Confirmed Information Or Something? Ha.

      (Above is my own guess. Separately, Gemini Pro said it was just a made up word.)

    • scared_together 1 hour ago
      And what’s stopping an AI agent from throwing in a casual NATCIOS here and there?
    • nine_k 56 minutes ago
      Likely the point of NATCIOS is exactly in being a made-up word not found anywhere, so a model won't utter it.
  • luk212 1 hour ago
    Bad patches are of course bad, but creating confident-looking noise for maintainers who are already stretched thin...now that's not good!

    Issue trackers and PRs are definitely getting harder and harder to trust. That said, AI is helping ALOT in OSS, but we definitely need guardrails around provenance, automated issue actions, and sudden changes in a contributor’s behavior.

    • g-b-r 39 minutes ago
      How is it helping a lot?
      • darknavi 36 minutes ago
        I personally find the barrier of starting new (FOSS) projects much lower now days.
        • Waterluvian 31 minutes ago
          Do they have value? Purpose?

          I vibe code shop jigs all the time but I don’t FOSS them because they rarely have value outside my context.

        • beepbooptheory 17 minutes ago
          It's like... 10 million trello clones in rust with exactly seven commits made on the same day three months ago.
        • g-b-r 33 minutes ago
          And how's the quality of these vibe-coded new foss projects?
        • bandrami 17 minutes ago
          What if -- and bear with me here -- that barrier was actually a good thing?
  • keyle 1 hour ago
    There is a natural pace of humans requiring food, water and sleep. The main issue with suspicious AI agents is that they never sleep. So it will take extra-coordination between timezones to ensure we don't let them in.

    Fundamentally, until we can really prove we're humans online, open-source has a real problem on its hands. Contributions from people from identities known and consistent before the AI-age are fine, everyone else is suspicious. LGTM is a big risk nowadays.

    • scared_together 1 hour ago
      > Contributions from people from identities known and consistent before the AI-age are fine

      Unfortunately, according to the article:

      > Giovannini has participated in discussions at least as far back as 2018, and his activity in Bugzilla goes back to at least 2016. He does not appear to have been a particularly active contributor to the project, but his involvement clearly predates the agentic AI era. Whether his account is now being operated by a human attacker, an agentic AI, or a mix of both, it has a legitimate history prior to its recent activity.

      So people would have to not only verify the age of Giovanni’s accounts, but judge whether his behaviour was normal.

  • aquariusDue 1 hour ago
    At first I wanted to make a silly joke along the lines of "get your agents in line and behaving!" but as I read on it became a pretty scary situation.

    Setting aside the potential supply chain attack I'm worried about the time lost going around these wild goose chases that unsupervised AI agents tend to throw other people on the receiving end on. Not only is there a lot of time lost on the maintainers side if they take this stuff seriously (and they seem to generally do) but on the side of the agents' wrangler how can they deem it OK to treat other people like this? While the solution would be to employ common decency, the tried and tested approach of you put in effort to write this so I guess I'll make some effort to read it, I feel that due to the onslaught of this kind of drive-by contributions (I think people have generally started to call them) will lead to a funny situation of having agents talk to each other on public forums basically.

    Anyway, I went on a tangent but man the times we're living in are a bit extra wild compared to the previous wild times in recent history.

  • marcus_holmes 12 minutes ago
    Bad title. This isn't an agent "running amok", this is an early experiment in carrying out an Xz attack by using an agent to build trust (and hacking/impersonating a known-good contributor identity). The agent is obeying commands it was given, the exact opposite of running amok, and although the execution isn't particularly effective, it is having some success (patches have been accepted).

    This is deeply scary, not because "agents are running amok" but because a huge amount of our infrastructure is vulnerable to this kind of attack, and if bad people are utilising LLM agents to carry them out, we're in for a wild ride over the next few years.

    • hn773746483 6 minutes ago
      It's just social engineering. No different than say, 2FA fatigue (blowing up someone's phone with 2FA "is this you? yes/no" prompts until user/child/wife/SO/etc clicks yes) or even just simply harassing IT helpdesk until they reset "your" password.
  • blop 1 hour ago
    looks like LLMs aren't mature enough yet to play long-game xz-style attacks without detection... Scary stuff though :( These supply chain attacks are getting really wild
  • ruguo 2 hours ago
    Prompt injection?

    Or is this simply another example of why autonomous agents shouldn't get write access before earning trust?

  • pianopatrick 2 hours ago
    "Someone using an AI agent ran amok in Fedora and elsewhere"
    • scared_together 1 hour ago
      Read closer - Giovanni’s accounts may have been compromised.
      • pianopatrick 40 minutes ago
        Sure, but I would expect that the compromise and the agent were both done by some person or group, not by an agent going rogue
      • hamdingers 9 minutes ago
        Given the history of the account it does not seem reasonable to take that claim seriously.
  • deadbabe 12 minutes ago
    Shit like this makes me think it’s time we start regulating the software engineering discipline into formal certifications and licensing and then we ONLY take seriously any code developed by someone with such qualifications, and they must be very strict qualifications none of this self-taught bootcamp BS.

    There is no other solution to agentic onslaught.

  • rimonu 2 hours ago
    [dead]