Malware & Ransomware

Kimi K3 and GLM 5.2 can create undetectable malware for $2
Malware & Ransomware

Kimi K3 and GLM 5.2 can create undetectable malware for $2

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…

NPM publish-time malware scanning and dual-use metadata
Malware & Ransomware

NPM publish-time malware scanning and dual-use metadata

As part of our ongoing supply-chain security work, npm is introducing automatic scanning of packages at publish time. This changelog covers what publishers can expect and a new metadata requirement…