apple and u2 would like a wordhttps://grith.ai/blog/clinejection-when-your-ai-tool-installs-another
-
apple and u2 would like a word
https://grith.ai/blog/clinejection-when-your-ai-tool-installs-another
This is old news.
What I want to know is what other threat actors are using OpenClaw for c2. -
apple and u2 would like a word
https://grith.ai/blog/clinejection-when-your-ai-tool-installs-another@Viss U2 is no longer the most annoying thing unexpectedly installed on your computer
-
This is old news.
What I want to know is what other threat actors are using OpenClaw for c2.@joy oh my god this article tho
-
apple and u2 would like a word
https://grith.ai/blog/clinejection-when-your-ai-tool-installs-anotherbwahahaha this is insane
-
@joy oh my god this article tho
@joy this article implies openclaw is the c2
-
bwahahaha this is insane
@Viss dayam
-
R relay@relay.infosec.exchange shared this topic
-
@joy this article implies openclaw is the c2
Yeah, the one thing that is new is the number of machines (4000) that were compromised.
-
bwahahaha this is insane
@Viss One thing I really dislike about the wording is that it implies that sanitisation of data inserted into prompts is possible. As far as I understand there is no reliable way to do that.
-
@Viss One thing I really dislike about the wording is that it implies that sanitisation of data inserted into prompts is possible. As far as I understand there is no reliable way to do that.
@mlen thats right. at present no llm can tell the difference between instructions and data
-
bwahahaha this is insane
@Viss so glad we dedicated billions of dollars to build datacenters filled with GPUs that allow us to (checks notes) turn everything everywhere into a potential RCE vulnerability.
