Malicious Fake OpenAI Repository on Hugging Face Distributes Infostealer Malware
A malicious repository on Hugging Face, impersonating OpenAI's 'Privacy Filter' project, reached the platform's trending list and distributed infostealer malware to Windows users. The repository, named Open-OSS/privacy-filter, accumulated approximately 244,000 downloads (though potentially inflated) before being removed. The malware was designed to steal sensitive data, including browser credentials, cryptocurrency wallets, VPN logins, developer secrets, Discord tokens, and SSH/FTP credentials. Researchers at HiddenLayer discovered the campaign on May 7, 2026, and Hugging Face subsequently disabled access to the malicious model.
Signal context
First seen: May 9, 2026
Last updated: Jun 26, 2026
Status: Public signal
Key points
- A malicious repository impersonating OpenAI's 'Privacy Filter' project was hosted on Hugging Face.
- The repository distributed infostealer malware to Windows users.
- It reached the #1 trending position on Hugging Face with approximately 244,000 downloads (potentially inflated).
Signal analysis
BetaThis analysis groups the signal by industry, likely incident action and impacted security area. It helps compare this signal with other published signals without treating the labels as final determinations.
Sector: Information
Likely country: Location not provided
Watch ransomware, endpoint compromise and business interruption exposure.
- Source type: outside the affected organization
Impact area: Confidentiality
- 26 signals in the same sector
- 90 signals with the same likely impact area
- 1 signal linked to this organization/domain
External sources
Fake OpenAI repository on Hugging Face pushes infostealer malware - Bleeping Computerhttps://www.bleepingcomputer.com/news/security/fake-openai-repository-on-hugging-face-pushes-infostealer-malware/Public source from bleepingcomputer.com.
Malicious Hugging Face model masquerading as OpenAI release hits 244K downloads - TechRadarhttps://www.techradar.com/news/a-fake-openai-repository-has-taken-top-spot-on-hugging-face-but-all-it-does-is-push-infostealer-malwarePublic source from techradar.com.
Fake OpenAI Privacy Filter Repo Hits #1 on Hugging Face, Draws 244K Downloads - The Hacker Newshttps://thehackernews.com/2026/05/fake-openai-privacy-filter-repo-hits-1.htmlPublic source from thehackernews.com.
Related signals
Grouped by why the signal is relevant.
eogb.co.uk Hit by Stormous Ransomware Group
eogb.co.uk, a UK-based organization, was claimed as a victim by the Stormous ransomware group. The incident was discovered on June 28, 2026, at 21:29 UTC, with deep access to Microsoft Dynamics GP, internal legal documents, partnership agreements, customer contracts, operational spreadsheets, financial reports, and executive documents.
Latvijas Valsts Mezi (LVM) Suffers Cybersecurity Breach
Latvia's state-owned company Latvijas Valsts Mezi (LVM) confirmed a cybersecurity breach of its IT systems, reported on June 26, 2026. The incident, discovered around June 22, led to hackers accessing LVM's IT infrastructure. External IT systems, including 'LVM GEO' and the 'Mednis' hunting app, were taken offline, along with some internal communication systems. A foreign ransomware group claimed responsibility for the attack, which raised concerns due to LVM's role in developing an electoral IT platform for Latvia's parliamentary elections.
Malicious 'Edgecution' Extension Exploits Microsoft Edge Native Messaging for Ransomware Deployment
Security researchers reported on June 25, 2026, the discovery of a new malware campaign dubbed 'Edgecution,' which utilizes a malicious Microsoft Edge extension to deploy ransomware and a Python-based backdoor. The extension abuses the Native Messaging API to escape the browser sandbox and establish a persistent system-level executor. Attackers are reportedly using Microsoft Teams for social engineering, directing victims to fake 'Outlook Updates Management Console' websites to trick them into installing the malicious extension. This campaign is believed to be operated by an Initial Access Broker (IAB) linked to the 'Payout Kings' ransomware operation.
Settra Suffers Ransomware Attack, Corporate Accounting Data Compromised
Settra, a company based in Singapore, was impacted by a ransomware attack with an estimated attack date of June 11, 2026. The attackers gained deep access to Microsoft Dynamics GP, compromising complete corporate accounting, invoices, and vendor details. This incident was disclosed on Ransomware.live.
NIFTY Corporation Affected by KDDI Corporation Data Breach
NIFTY Corporation, a Japanese internet service provider, was impacted by a data breach originating from an email system provided by KDDI Corporation. Threat actors gained unauthorized access to this shared system by exploiting a vulnerability in third-party software. This led to the potential exposure of up to 14.2 million email addresses and passwords across all affected ISPs. NIFTY Corporation customers' email addresses and passwords may have been compromised.
BIGLOBE Inc. Affected by KDDI Corporation Data Breach
BIGLOBE Inc., a Japanese internet service provider, was impacted by a data breach originating from an email system provided by KDDI Corporation. Threat actors gained unauthorized access to this shared system by exploiting a vulnerability in third-party software. This led to the potential exposure of up to 14.2 million email addresses and passwords across all affected ISPs. BIGLOBE Inc. customers' email addresses and passwords may have been compromised.