惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园_首页
C
Check Point Blog
B
Blog RSS Feed
G
Google Developers Blog
H
Help Net Security
博客园 - Franky
Blog — PlanetScale
Blog — PlanetScale
H
Hackread – Cybersecurity News, Data Breaches, AI and More
量子位
Recent Announcements
Recent Announcements
B
Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
D
DataBreaches.Net
小众软件
小众软件
T
The Blog of Author Tim Ferriss
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
MongoDB | Blog
MongoDB | Blog
Y
Y Combinator Blog
T
Tailwind CSS Blog
J
Java Code Geeks
MyScale Blog
MyScale Blog
雷峰网
雷峰网
有赞技术团队
有赞技术团队
博客园 - 聂微东

Latest from TechRadar in Security

Robots are fighting wars and helping to quash riots — China is arming riot police with squads of AI controlled drones and Ukraine wants to man the frontlines with 25,000 robots US security agency still using Mythos despite ban – government using new security tool despite Pentagon's… Struggling to launch Teams? Microsoft recalls update causing failed startup and infinite loading loops –… How to meaningfully measure the effectiveness of cyber resilience 'We've identified a security incident': Vercel breach confirmed after hackers claim stolen data for sale… How EU organizations can turn sovereign cloud theory into action 'Update immediately': 60,000 WordPress websites at risk after experts discover flaw that allows hackers to… 'They mopped the floor with me and pulled every childish game they could': Disgruntled researcher releases second major Windows zero-day — claims Microsoft 'would ruin my life, and they did' 'As threats evolve, Gemini keeps our defenses one step ahead': Google claims its AI helped it block over 8.3… Cisco tells Webex users to patch critical security flaws immediately, as experts find its Wi-Fi boxes may be filling their disks with undeletable data every day Microsoft experts warn North Korean attackers target macOS users with 'a highly reliable infection chain' to steal passwords, financial data and more — here's how to stay safe Solving the shadow IT crisis in travel Agentic swarms will change how everyone uses AI – but how can organizations deploy them securely? Europol launches Operation PowerOFF — warns 75,000 DDoS users and takes down 53 domains China completes testing on ‘deep-sea electro-hydrostatic actuator’ capable of slicing undersea cables as deep as 3.5 kilometers – new compact subsea vessel testing bridges the ‘last mile’ and could deploy in 2026 Many are still leaving the door open': Security experts warn FIFA World Cup partners could be putting customers at… 'Anyone with $10 could have walked straight through': Report warns this legit-looking software is actually… An ancient Microsoft Excel security flaw could let hackers hijack your entire system, so patch now 'This is not a traditional coding error': Experts flag potentially critical security issues at the heart of Anthropic's MCP, exposes 150 million downloads and thousands of servers to complete takeover Your OpenClaw agents can empty your inbox and leak your data. Here's how to secure them Russia hits European thermal power plant in attempted ‘destructive’ cyberattack – Pro-Kremlin hackers are engaging in ‘riskier and more reckless behavior’ in latest attempt to cripple Western critical infrastructure The war in Iran is reaching cyberspace - here’s how to prepare Millions of hotel goers may have been exposed after hackers steal data and leak it on Telegram 'Every Apple user needs to know about this nasty scam': Fake warnings tell users their iCloud data will be… Dozens of WordPress plugins hijacked to target thousands of sites 'We are currently being extorted' — crypto giant Kraken says it is facing extortion attack, here's… McGraw Hill becomes latest to see its Salesforce data hacked Over 100 Chrome Web Store extensions found stealing user data from thousands of accounts OpenAI reveals its Mythos rival designed for cybersecurity pros When cyberattacks are inevitable, recovery becomes the strategy
A fake OpenAI repository has taken top spot on Hugging Fa...
Sead Fadilpa · 2026-05-11 · via Latest from TechRadar in Security
A robot standing thoughtfully in front of a giant digital display with code on it
(Image credit: Getty Images)

  • Attackers typosquatted an OpenAI repo on HuggingFace, distributing an infostealer disguised as a “privacy filter” model
  • The malware disabled SSL checks, escalated privileges, and deployed the sefirah payload to steal credentials, crypto wallets, and system data
  • The fake repo hit 244,000 downloads and briefly topped HuggingFace rankings before removal, with other linked malicious repos also taken down

Cybercriminals were able tp spoof OpenAI products to distribute an infostealer malwar to more than 240,000 computers before being spotted and eliminated, experts have warned.

Security researchers HiddenLayer said they spotted a new repository on HuggingFace called Open-OSS/privacy-filter.

The privacy filter repository is, according to HiddenLayer, a typosquatted version of the official release, which came with a model card that was copied “nearly verbatim”. The loader.py file that was shipped in it fetches and executes an infostealer, they added.

Rising to the top

Before dropping the infostealer, the malware first disabled SSL verification, decoded a base64 URL, and from it downloaded a JSON payload with a PowerShell command. This command, in turn, downloaded a batch file that escalated privileges, deployed the ‘sefirah’ payload, added it to Microsoft Defender’s exclusion list, and then ran it.

The infostealer itself does what most infostealers do - grabs data saved in browsers, exfiltrates discord tokens, local databases, and master keys, steals cryptocurrency wallet information, browser extension data, SSH, FTP, VPN credentials, as well as sensitive files stored locally. It can also grab screenshots, exfiltrate system information, and more.

The download count on the fake repository is massive - 244,000 downloads in mere days.

However, this doesn’t mean every download led to an infection. BleepingComputersays the download numbers may have been inflated, and that the repository itself was “liked” by 667 auto-generated accounts. Still, even if it was all fake, the repository still managed to hit #1 on Hugging Face for a brief moment, which definitely could have lead to infections.

Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!

However, by following the trail of the fake accounts, HiddenLayer was able to expose other, less-successful repositories, which were also malicious and used the same infrastructure. All of these have since been removed from the platform.


Best antivirus software header

Google logo on a black background next to text reading 'Click to follow TechRadar'

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.


Sead is a seasoned freelance journalist based in Sarajevo, Bosnia and Herzegovina. He writes about IT (cloud, IoT, 5G, VPN) and cybersecurity (ransomware, data breaches, laws and regulations). In his career, spanning more than a decade, he’s written for numerous media outlets, including Al Jazeera Balkans. He’s also held several modules on content writing for Represent Communications.