Comment on The rise of Moltbook suggests viral AI prompts may be the next big security threat
suicidaleggroll@lemmy.world 2 weeks ago
Clawdbot, OpenClaw, etc. are such a ridiculously massive security vulnerability, I can’t believe people are actually trying to use them. Unlike traditional systems, where an attacker has to probe your system to try to find an unpatched vulnerability via some barely-known memory overflow issue in the code, with these AI assistants all an attacker needs to do is ask it nicely to hand over everything, and it will.
This is like removing all of the locks on your house and protecting it instead with a golden retriever puppy that falls in love with everyone it meets.
You know, in IT security, the weakest link will always be the users… they are easy to fool, they just blindly trust whatever you tell them.
But now, thanks to AI, computers will finally catch up to humans in their ability to be tricked. No longer will you need human users to set their password to easy things to remember. Our new AIs will actually be capable of shortening their encryption key to a common name, and leaving them on post it notes on their desks.
XLE@piefed.social 2 weeks ago
Have you tried asking the puppy to be a better guard dog? That’s how the AI safety professionals do it.