Elektrine lite

← Feed

@briankrebs__dup_6@infosec.exchange

2026-01-27 21:17 UTC

Letting AI agents run your life is like handing the car keys to your 5-year-old. What could go wrong? I was marveling while reading this PCMag piece, which describes how to secure an agentic AI setup that essentially mimics malware: To do it's job properly, the AI agent has to be able to read private messages, store credentials, execute commands, and maintain a persistent state. How do you do that? You chase after it like you would your child. "The important thing is to make sure you limit "who can talk to your bot, where the bot is allowed to act, [and] what the bot can touch" on your device, the bot's support documentation says." https://www.pcmag.com/news/clawdbot-moltbot-hot-new-ai-agent-creator-warns-of-spicy-security-risks?test_uuid=04IpBmWGZleS0I0J3epvMrC&test_variant=A

Replies (15)

  • @tknarr@mstdn.social 2026-01-27 21:22

    @briankrebs@infosec.exchange Sounds like "Do not look into laser with remaining eye."

    Open ##5332053

  • @briankrebs@infosec.exchange old style thinking about new stuff If you start working on this ping me and we can talk

    Open ##5332054

  • @womble@infosec.exchange 2026-01-27 21:25

    @briankrebs@infosec.exchange if there's one thing that the entire history of humanity has taught us, it's that as a species we are great at making nuanced, highly context-specific decisions with incomplete information. I foresee that this is going to turn out great.

    Open ##5332062

  • @LeahPrice@hcommons.social 2026-01-27 21:31

    @briankrebs@infosec.exchange Makes you nostalgic for 1860, when machine-generated text meant a new magazine. (from PUNCH)

    Open ##5332063

  • @zl2tod@mastodon.online 2026-01-27 21:49

    @briankrebs@infosec.exchange Thread re #clawdbot : https://infosec.exchange/@munin/115963686278347109

    Open ##5332066

  • @crouton@aus.social 2026-01-27 21:52

    @briankrebs@infosec.exchange This sounds like the optimally worst implementation of a digital assistant. I was looking for a distant variant of this, where I set the (mostly deterministic) rules and actions, etc. Kinda like HA/node-red but aimed at being an assistant rather than controlling a house. Giving it a blank cheque and hooking up to a LLM is insane.

    Open ##5332068

  • @hal8999@infosec.exchange 2026-01-27 22:02

    @briankrebs@infosec.exchange The stories are writing themselves: My A.I. agent took over my finances, framed me for sex trafficking, then unlocked the doors and turned on lights for the police.

    Open ##5332070

  • @carsten@minnesotasocial.net 2026-01-27 22:09

    @briankrebs@infosec.exchange and if the bot "touches" something it was not allowed to touch? "Sorry, me bad, won't do it again, probably" - does it again.

    Open ##5332078

  • @theorangetheme@en.osm.town 2026-01-27 22:30

    @briankrebs@infosec.exchange It's fucking bonkerstown. You might as well just wire up a random number generator and every 1/10 times it just deletes your home directory. At least that achieves the same result but with a fraction of the electricity and human rights abuses.

    Open ##5332083

  • @briankrebs@infosec.exchange So sayeth the bot. It is smarter not to talk to them in the first place.

    Open ##5332087

  • @craignicol@glasgow.social 2026-01-27 23:25

    @briankrebs@infosec.exchange ok child, you can have the scissors, but only if you promise not to run with them

    Open ##5332093

  • @briankrebs@infosec.exchange Getting so desperate with that market bubble that they give a last dying shot at making SkyNet. Do they ever give the hell up?

    Open ##5332095

  • @grumpydad@infosec.exchange 2026-01-28 05:01

    @briankrebs@infosec.exchange 4-year-old me drove our family car into a hedge (managed to steal the keys from dad). I actually think I'd do a better job as a 5-year-old. Definitely better to han any "AI" would ever run your life anyway.

    Open ##5332096

  • @li-da-da411@thebrainbin.org 2026-01-28 06:48

    @briankrebs@infosec.exchange I do not deny the allure of artificial intelligence. However, I believe it must be employed correctly, serving merely as a reference. Many things can only be fully understood through personal experience. Recently, with the aid of artificial intelligence and drawing upon my own experiences, I have written an article on Yacht Import Regulations.

    Open ##5332097

  • @b_age@troet.cafe 2026-01-28 11:12

    @briankrebs@infosec.exchange i misread the first few words as "letting AI agents ruin your life ..." and i don't really see a difference

    Open ##5332098