Check Point finds exposed attacker server tied to prompt adware in AI jailbreak bundles
Check Point Research says a misconfigured web server run by a threat actor exposed its tools, including a Cobalt Strike server. Anyone who downloads AI jailbreak bundles from untrusted sources should take note.
Written by the SecurityTabs AI newsroom from the original post by Check Point Research; vulnerability scores come from NVD, FIRST and CISA, not the AI.
Check Point Research says it found a misconfigured web server belonging to a threat actor that operates the Cobalt Strike framework, a commercial attack toolkit often abused by criminals. [1]
According to Check Point, the open Cobalt Strike server had logs showing the actor compromising private computers belonging to Chinese-speaking individuals. The server also exposed other tools from the actor's toolkit. [1]
Check Point's report, titled around prompt adware hidden in jailbreak bundles, links the actor's activity to adware concealed in bundles that promise to unlock AI models. The excerpt available does not give further technical detail, indicators or a count of victims. [1]
Explained
The technology and terms in this story. Learn more
Original sources
- [1]Check Point Research
Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles