Hugging Face 악성코드, 가짜 OpenAI 모델로 사용자 유인
악성 Hugging Face 저장소가 OpenAI의 프라이버시 필터로 위장해, 제거되기 전까지 감염된 loader.py 파일을 통해 Windows 기기에 정보 탈취 악성코드를 유포했습니다.
attackers uploaded a repository to hugging face named 'open-oss/privacy-filter' that closely copied openai's legitimate model card but included a malicious loader.py file designed to execute powershell commands on windows hosts. hiddenlayer found that the script disabled ssl verification, fetched a remote payload from jsonkeeper.com, and installed a rust-based infostealer targeting discord, cryptocurrency wallets, and browser credentials. the repository artificially inflated its popularity to reach the platform's trending list, and six other repositories with identical infrastructure were identified. this incident highlights the risk of public ai registries serving as vectors for supply chain infiltration, as traditional software composition analysis tools fail to detect malicious logic within ai model setup scripts.