Well we all knew this was finally going to happen....
Researchers in Google's Threat Intelligence Group have discovered two new malware strains — PromptFlux and PromptSteal — that use large language models to change their behavior mid-attack.
The game of cat and mouse for cyberattacks just took a huge and unprecedented step forward that will be interesting to see how quickly defenses can be put up to address this.
Researcher found the PromptFlux
appears to be in active development: Researchers observed the author uploading updated versions to VirusTotal, likely to test how good it is at evading detection. It uses Gemini to rewrite its own source code, disguise activity and attempt to move laterally to other connected systems.