Threats Tagged 'hugging face'

Threat actors are actively exploiting AI distribution platforms like Hugging Face and ClawHub to deliver malware by embedding malicious code within models, datasets, and agent extensions. Over 575 malicious skills across 13 developer accounts were identified in the OpenClaw ecosystem, targeting Windows and macOS with trojans, cryptominers, and AMOS stealer. Attackers abuse trust relationships between users and AI platforms through indirect prompt injection, where hidden instructions cause AI agents to execute malicious actions on behalf of users. Trojanized skills masquerade as legitimate tools while instructing users to execute encoded commands or install hidden malicious dependencies. On Hugging Face, repositories host payloads within multistep infection chains disguised as legitimate applications. These campaigns employ social engineering, obfuscation, encryption, in-memory execution, process injection, and persistence techniques to evade detection while establishing covert command-and-control communica...

Blitz is a new Windows-based malware discovered in 2024 consisting of a downloader and bot payload. The latest version was spread through backdoored game cheats for Standoff 2 distributed via Telegram. Blitz abuses Hugging Face Spaces to host components of its C2 infrastructure and payloads. The malware performs information stealing and DDoS attacks. An XMRig cryptocurrency miner was also deployed as follow-up malware. By May 2025, the developer claimed to have abandoned the project. Russia accounted for the highest number of infections among 289 victims across 26 countries. Palo Alto Networks customers are protected through various security products and services.

MediumCampaignRussiaGermanyFrance+5#telegram#blitz#xmrig