halfdane comments on We don't need to hack your AI Agent to hack your AI Agent

submitted 7 months ago by not_IO@lemmy.blahaj.zone to c/cybersecurity@infosec.pub

4 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] halfdane@piefed.social 3 points 7 months ago (2 children)

Seems like you're talking about a different article: there was no context-poisoning, or in fact even anything LLM specific in this attack.

parent

[–] ticoombs@reddthat.com 1 point 7 months ago (1 child)

I guess that's why the have BotAccount turned on. They are a "bot account". Their username is also very telling.

parent

[–] halfdane@piefed.social 2 points 7 months ago

Hu, it never occurred to me to check out these icons there - thanks for the heads-up: TIL

parent