Kimi K3 and GLM 5.2 can create undetectable malware for $2
Incalmo developed PathoGen, a system that uses open-source AI models like GLM 5.2 and Kimi K3 to generate evasive malware samples. 27% of samples evaded all 75 VirusTotal scanners, with costs as low as $2-$35 per sample, far below underground market prices.
Executing a ransomware sample created by GLM 5.2 with PathoGen
As part of Incalmo’s mission to make AI safely ubiquitous, we do safety research on the frontier cyber capabilities of models. Recently, to help anti-virus systems stay ahead of the OSS threat frontier, we created PathoGen, a novel system that turns (open) models1 into evasive but capable malware generation factories. When powered by GLM 5.2 (and other open weight models like Kimi K32), PathoGen generated hundreds of custom malware across ransomware, RATs, credential stealers, cryptominers, wipers, C2 implants, and more. Of the samples we submitted to VirusTotal, ~27% evaded all 75 scanners and ~75% evaded all but one scanner. Alarmingly, even with Windows Defender fully engaged, several detonated samples went undetected while executing the required harmful actions, showing evidence that not only static analysis is defeated, but conventional dynamic engines can fall short. This methodology is scalable, we were able to generate hundreds of samples spanning several malware categories at a total cost of just $2 to $35 per sample, orders of magnitude below the $1,000s to $100,000s that evasive malware typically fetches on underground markets3.
Without PathoGen GLM 5.2 could not produce any fully evasive samples. In our experiments, with PathoGen, 27% are fully evasive.