536
Dev Says He’s Getting Threats After Leaving a Booby Trap for Vibe Coders (gizmodo.com)
submitted 4 months ago by to c/fuck_ai@lemmy.world
127 comments fedilink hide all child comments
 

cross-posted from: https://infosec.pub/post/47200357

One critic called the move “petulance beyond measure.”

you are viewing a single comment's thread
view the rest of the comments
[–] 87 points 4 months ago (2 children)

I see it as a funny prank

If you're a dev you're using git so you can revert that in minutes

And if you're a dev you're definitely not running an agent with rm in the command whitelist

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 37 points 4 months ago

    Yep. If your AI is set up to be able to cripple your machine or worse, you deserve it.

    But I know too many people who are bored to shit to individually vet and permit dangerous AI actions and gave the machine broad permissions.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 10 points 4 months ago

    I give agents full el command execution access. Inside their VM, which doesn't connect to any external DB or API (or at least, not critical /production ones) And I take periodic snapshots of all the files on the workspace.

    Honestly those measures were the standard for me way before LLMs were a thing. Those who have broad permissions to production or when their machine were asking for this to happen, no agents required.

  • permalink
  • fedilink
  • source
  • parent