125
A Meta AI security researcher said an OpenClaw agent ran amok on her inbox (techcrunch.com)
submitted 8 months ago by to c/technology@lemmy.world
14 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 8 months ago* (1 child)

Wait for real? I thought that was a joke about how badly it was designed?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 5 points 8 months ago

    Nope, it's real. OpenClaw has zero filters, zero guardrails, just an LLM with full access to your accounts and APIs with unrestricted access to the web, including reading and processing incoming messages from unknown senders. Attackers can do just about anything with it that they want simply by asking it nicely.

  • permalink
  • fedilink
  • source
  • parent