| Original Text |
|---|
Exploring a New KimJongRAT Stealer Variant and ItsPowerShell ImplementationDominik ReichelMalware25 min readRelated ProductsExecutive SummaryThis article provides a comprehensive analysis of two new variants of the KimJongRAT stealer. We combineour new research findings with existing knowledge to provide a comprehensive resource for understandingand combating these new KimJongRAT variants.The KimJongRAT stealer was first described in 2013 by the Malware.lu CERT [PDF]. We documented anothervariant of this family in 2019.One of the new variants uses a Portable Executable (PE) file and the other uses a PowerShell implementation.The PE and PowerShell variants are both initiated by clicking a Windows shortcut (LNK) file that downloads adropper file from an attacker-controlled content delivery network (CDN) account. The PE variant’s dropperdeploys a loader, a decoy PDF and a text file. The dropper in the PowerShell variant deploys a decoy PDF filealong with a ZIP archive.The loader downloads more malicious files, including the stealer component for KimJongRAT.The PowerShell variant's dropper file deploys a decoy PDF file and a ZIP archive containing scripts thatinclude the KimJongRAT PowerShell-based stealer and keylogger components.Both variants are designed to gather and transfer victim information and browser data, including from crypto-wallet extensions, to the attacker’s server. The PE variant also collects FTP and email client information.The infection sequence uses a multi-file approach and a legitimate CDN service to mask its maliciousactivities.Palo Alto Networks customers are better protected from the malware samples described in this article throughAdvanced WildFire, Advanced URL Filtering, Advanced DNS Security and Advanced Threat Prevention.Cortex XDR and XSIAM are designed to prevent the execution of known malicious malware, and also preventthe execution of unknown malware using Behavioral Threat Protection and machine learning based on theLocal Analysis module.If you think you might have been compromised or have an urgent matter, contact the Unit 42 IncidentResponse team.Related Unit 42 TopicsPowerShell, Backdoor
New KimJongRAT PE VariantThis section details the new KimJongRAT variant that uses PE files as final payloads.The initial file of the execution chain is an LNK file, but we do not yet know how attackers distribute thesefiles. Figure 1 shows the execution flow of the most recent KimJongRAT variant.
Figure 1. Malware execution chain of the latest KimJongRAT PE variant (iconsources).Step 1: When double-clicked, the initial LNK file downloads an HTML Application (HTA) file from anattacker-controlled CDN account, saves it to disk and runs it as shown in Figure 1Step 2: The HTA file drops three embedded files sys.dll, sexoffender.pdf and user.txt to diskSexoffender.pdf is a decoy PDF file opened by the victim's default PDF readerThe HTA file executes the sys.dll loader
Step 3: The loader uses two payload URL strings in the user.txt file to retrieve two more files namedmain64.log and net64.logThese LOG files are a new KimJongRAT stealer component and an orchestratorStep 4: The orchestrator sends the collected information and data to a command and control (C2) server andawaits commands from the attackersTo more fully understand these steps, let’s examine the associated files.PE Variant Initial LNK FileWhen double-clicking one of the initial LNK files, the file uses the Windows tool cmd.exe to change thecurrent directory to the Windows %temp% folder (shown in the Local base path and Command line argumentsin Figure 2) . It then uses the Windows tool curl.exe to download an HTA file named pdf.hta from a legitimateCDN provider at cdn.glitch[.]global into the %temp% directory. The attacker abuses this service to host thenext and subsequent stages of the malware.The URL for the HTA file contains a parameter v with the string 1740535190239. This string is an epoch datethat translates to Wednesday, February 26, 2025, 1:59 a.m. (GMT).Finally, the LNK runs the downloaded HTA file using the Windows tool mshta.exe as shown in Figure 2.
Figure 2. Execution related LNK information as shown in LnkParse3.This LNK file contains unique metadata that can be used to find additional samples. Figure 3 shows the driveserial number, Windows OS version and machine ID of the system where the LNK file was created.Additionally, there is a Korean language string 응용 프로그램 (translated: application program) in the extradata section.
Figure 5. Deobfuscated version of pdf.hta as shown in Visual Studio Code.The Base64 string for the first payload starting with JVBERi0xL is decoded through the Windows toolcertutil.exe and dropped as the decoy PDF file sexoffender.pdf into the Windows %temp% directory. It is thenopened by the default application for PDF files.The Base64 string starting with aHR0cHM6L for the second payload is decoded and dropped as user.txt to the%localappdata% folder.The third Base64 string starting with TVqQAAMAAA is decoded and dropped as sys.dll, also to the%localappdata% folder. This HTA file then runs sys.dll using rundll32.exe using sys.dll's only exportedfunction named s.The dropped user.txt is a text file containing URLs to the same CDN sub-directory that hosts the maliciousHTA file, as shown in Figure 6.
Figure 6. The content of user.txt as shown in Windows Notepad.The last dropped file is named sys.dll, and it downloads the files from the URLs in user.txt and executes them.Second Stage Loader sys.dllThe second stage loader named sys.dll is a 64-bit DLL internally named baby.dll. It has a single exportedfunction named s that contains all the malware's functionality.When this function is called with rundll32.exe, it first checks whether the malware is running on a virtualmachine or sandbox as shown in Figure 7. If that is the case, the loader deletes itself and quits. If not, it createsa mutex named co_sys_co and starts a sub-thread.
Figure 3. Metadata from the LNK file as shown in LnkParse3.PE Variant First Stage HTA FileThe LNK sample we analyzed downloaded and saved an HTA file named pdf.hta to the Windows %temp%directory. This HTA file contains obfuscated VBS code. Additionally, the HTA file has three embeddedpayloads appended after the code as Base64 text.Figure 4 shows an excerpt of the HTA file with the obfuscated VBS code and the start of the Base64-encodedpayloads.
Figure 4. Excerpt of the pdf.hta file content as shown in Visual Studio Code.Figure 5 shows the deobfuscated version of this HTA file with the truncated Base64-encoded payloads.
Figure 7. Decompiled source code of exported function s from sys.dll as shown in IDA Pro.The sub-thread checks if any previously dropped payloads are present in the %localappdata%\net directory. Ituses this directory to store downloaded payloads from the attacker’s CDN stager URL.The sys.dll loader expects any files downloaded to this folder to be encrypted data binaries with the first 16bytes being the RC4 decryption key for the remaining bytes. When it finds a file in this folder, it decrypts,executes and finally deletes the file.After creating the sub-thread, the malware reads the URLs from the %localappdata%\user.txt file previouslydropped by the HTA file. It appends the date and time in epoch format as ?v=[epoch time] to each URL string.Afterwards, it contacts the CDN service to download the RC4-encrypted file net64.log into the%localappdata%\net folder to load it reflectively.This net64.log file is the new KimJongRAT stealer component. It endlessly runs a loop that only exits if the file%localappdata%\micro.log.zip is present. This file is created by net64.log and contains the victim’s stoleninformation and data.When micro.log.zip is detected, the sys.dll loader downloads the second RC4-encrypted file main64.log fromthe CDN server and stores it as notepad.log. As soon as notepad.log is written to %localappdata%\net, the sub-thread reads, decrypts, executes and deletes it. This decrypted file is the main orchestrator that implementsnetwork, backdoor and information-stealing functionality.Third Stage Orchestrator and BackdoorThe downloaded payload main64.log is internally named NetworkService.dll and has a compilation timestampof December 3, 2024, 7:36 a.m. UTC. Figure 8 shows its PDB file path.
Figure 8. PDB file path of net64.log as shown in EXE Explorer.As noted in Figure 8, the software has a PDB file path that includes the string\research\Spyware\Advanced\Covaware. A 2019 article by ESTsecurity describes a campaign namedOperation Giant Baby where attackers used malware with the same name in activity relating to our BabySharkarticle from the same year.This main64.log file is the main orchestrator that handles output created by the other downloaded filenet64.log. While main64.log is primarily responsible for the network communication and backdoorfunctionality, net64.log is responsible for stealing credentials from browser and email or FTP clients.The main orchestrator has a single exported function named fool, which contains the majority of themalware’s functionality. The DllMain entry point is only used for various initialization routines. These
routines create multiple directories associated with the base C2 URL and file paths that the malware useslater.As a unique victim ID, main64.log uses the volume serial number. If the volume serial number cannot beobtained, main64.log uses a combination of the computer and username for the victim ID. It encodes thisalternative ID value as a Base64 string, as shown in Figure 9.
Figure 9. Decompiled C2 base URL creation function from main64.log as shown in IDA Pro.However, this alternative ID is not used throughout the malware’s code and thus seems to be leftover codefrom earlier versions of this malware. After establishing the unique ID, main64.log calls the exported functionfool before finally writing the clipboard data into a file.The exported function fool shown in Figure 10 starts four threads before infinitely looping through a sleep call.
Figure 10. Decompiled C2 string creation function from main64.log as shown in IDA Pro.These threads are named as follows:main_threadclipboard_log_to_netkey_file
keylogger_log_window_title_and_keyskeylogger_flush_to_netkey_fileThe first thread named main_thread shown below in Figure 11 implements the network, backdoor andinformation stealing functionality. The other three threads are dedicated to recording keystrokes, windowtitles and clipboard information.
Figure 11. Decompiled main_thread from main64.log as shown in IDA Pro.The network communication is implemented in an infinite loop that uploads collected data and requestscommands from the C2 server. This malware implements three methods to communicate with the C2 server.To upload data or files, it uses the HTTP POST method with multipart/form-data, which we will subsequentlydescribe as HTTP POST multi, or application/x-www-form-urlencoded, which we will call HTTP POST app.To download data, the malware uses an HTTP GET request.Figure 12 shows the initial network capture where the stolen browser data and the system information are sentto the C2 server.
Figure 12. Initial network communication with the C2 server as shown in Wireshark.At first, the file micro.log.zip from the %localappdata% directory is copied into the %temp% directory asmicro.log.zip_. This file is then uploaded to the C2 server with an HTTP POST multi request and the hard-coded boundary string ----------sdfaffi3457839sfhjkaskl. Before it is uploaded as a value of the key file0, theZIP archive is XORed with the key 0xFE.Additionally, two keys val and id with the values delete and the volume serial number are sent to the C2 server.The former is most likely a note that the original file micro.log.zip is deleted after its copy gets uploaded, whilethe latter is used to associate the ZIP archive to a specific victim.The HTTP POST multi method is always used to send file data, as is the same schema described above:Key: val, value: deleteKey: id, value: |
| Original Text | ChatGPT 4o Paged |
|---|---|
Exploring a New KimJongRAT Stealer Variant and ItsPowerShell ImplementationDominik ReichelMalware25 min readRelated ProductsExecutive SummaryThis article provides a comprehensive analysis of two new variants of the KimJongRAT stealer. We combineour new research findings with existing knowledge to provide a comprehensive resource for understandingand combating these new KimJongRAT variants.The KimJongRAT stealer was first described in 2013 by the Malware.lu CERT [PDF]. We documented anothervariant of this family in 2019.One of the new variants uses a Portable Executable (PE) file and the other uses a PowerShell implementation.The PE and PowerShell variants are both initiated by clicking a Windows shortcut (LNK) file that downloads adropper file from an attacker-controlled content delivery network (CDN) account. The PE variant’s dropperdeploys a loader, a decoy PDF and a text file. The dropper in the PowerShell variant deploys a decoy PDF filealong with a ZIP archive.The loader downloads more malicious files, including the stealer component for KimJongRAT.The PowerShell variant's dropper file deploys a decoy PDF file and a ZIP archive containing scripts thatinclude the KimJongRAT PowerShell-based stealer and keylogger components.Both variants are designed to gather and transfer victim information and browser data, including from crypto-wallet extensions, to the attacker’s server. The PE variant also collects FTP and email client information.The infection sequence uses a multi-file approach and a legitimate CDN service to mask its maliciousactivities.Palo Alto Networks customers are better protected from the malware samples described in this article throughAdvanced WildFire, Advanced URL Filtering, Advanced DNS Security and Advanced Threat Prevention.Cortex XDR and XSIAM are designed to prevent the execution of known malicious malware, and also preventthe execution of unknown malware using Behavioral Threat Protection and machine learning based on theLocal Analysis module.If you think you might have been compromised or have an urgent matter, contact the Unit 42 IncidentResponse team.Related Unit 42 TopicsPowerShell, Backdoor |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Delivery
Phase: Download
Phase: Collection
Phase: Exfiltration
This structured information allows red teams to effectively emulate the tactics and procedures used by the threat actor. |
New KimJongRAT PE VariantThis section details the new KimJongRAT variant that uses PE files as final payloads.The initial file of the execution chain is an LNK file, but we do not yet know how attackers distribute thesefiles. Figure 1 shows the execution flow of the most recent KimJongRAT variant. Figure 1. Malware execution chain of the latest KimJongRAT PE variant (iconsources).Step 1: When double-clicked, the initial LNK file downloads an HTML Application (HTA) file from anattacker-controlled CDN account, saves it to disk and runs it as shown in Figure 1Step 2: The HTA file drops three embedded files sys.dll, sexoffender.pdf and user.txt to diskSexoffender.pdf is a decoy PDF file opened by the victim's default PDF readerThe HTA file executes the sys.dll loader |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Payload Delivery
Phase: Decoy Strategy
Phase: Execution
|
Step 3: The loader uses two payload URL strings in the user.txt file to retrieve two more files namedmain64.log and net64.logThese LOG files are a new KimJongRAT stealer component and an orchestratorStep 4: The orchestrator sends the collected information and data to a command and control (C2) server andawaits commands from the attackersTo more fully understand these steps, let’s examine the associated files.PE Variant Initial LNK FileWhen double-clicking one of the initial LNK files, the file uses the Windows tool cmd.exe to change thecurrent directory to the Windows %temp% folder (shown in the Local base path and Command line argumentsin Figure 2) . It then uses the Windows tool curl.exe to download an HTA file named pdf.hta from a legitimateCDN provider at cdn.glitch[.]global into the %temp% directory. The attacker abuses this service to host thenext and subsequent stages of the malware.The URL for the HTA file contains a parameter v with the string 1740535190239. This string is an epoch datethat translates to Wednesday, February 26, 2025, 1:59 a.m. (GMT).Finally, the LNK runs the downloaded HTA file using the Windows tool mshta.exe as shown in Figure 2. Figure 2. Execution related LNK information as shown in LnkParse3.This LNK file contains unique metadata that can be used to find additional samples. Figure 3 shows the driveserial number, Windows OS version and machine ID of the system where the LNK file was created.Additionally, there is a Korean language string 응용 프로그램 (translated: application program) in the extradata section. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Delivery
Phase: Command and Control
|
Figure 5. Deobfuscated version of pdf.hta as shown in Visual Studio Code.The Base64 string for the first payload starting with JVBERi0xL is decoded through the Windows toolcertutil.exe and dropped as the decoy PDF file sexoffender.pdf into the Windows %temp% directory. It is thenopened by the default application for PDF files.The Base64 string starting with aHR0cHM6L for the second payload is decoded and dropped as user.txt to the%localappdata% folder.The third Base64 string starting with TVqQAAMAAA is decoded and dropped as sys.dll, also to the%localappdata% folder. This HTA file then runs sys.dll using rundll32.exe using sys.dll's only exportedfunction named s.The dropped user.txt is a text file containing URLs to the same CDN sub-directory that hosts the maliciousHTA file, as shown in Figure 6. Figure 6. The content of user.txt as shown in Windows Notepad.The last dropped file is named sys.dll, and it downloads the files from the URLs in user.txt and executes them.Second Stage Loader sys.dllThe second stage loader named sys.dll is a 64-bit DLL internally named baby.dll. It has a single exportedfunction named s that contains all the malware's functionality.When this function is called with rundll32.exe, it first checks whether the malware is running on a virtualmachine or sandbox as shown in Figure 7. If that is the case, the loader deletes itself and quits. If not, it createsa mutex named co_sys_co and starts a sub-thread. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Defense Evasion
Phase: Persistence
Phase: Command and Control (C2)
|
Figure 3. Metadata from the LNK file as shown in LnkParse3.PE Variant First Stage HTA FileThe LNK sample we analyzed downloaded and saved an HTA file named pdf.hta to the Windows %temp%directory. This HTA file contains obfuscated VBS code. Additionally, the HTA file has three embeddedpayloads appended after the code as Base64 text.Figure 4 shows an excerpt of the HTA file with the obfuscated VBS code and the start of the Base64-encodedpayloads. Figure 4. Excerpt of the pdf.hta file content as shown in Visual Studio Code.Figure 5 shows the deobfuscated version of this HTA file with the truncated Base64-encoded payloads. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
In this scenario, further specific commands for emulation would require deobfuscation and decoding of the Base64 payloads contained within the HTA file, which may reveal additional execution or persistence techniques. |
Figure 7. Decompiled source code of exported function s from sys.dll as shown in IDA Pro.The sub-thread checks if any previously dropped payloads are present in the %localappdata%\net directory. Ituses this directory to store downloaded payloads from the attacker’s CDN stager URL.The sys.dll loader expects any files downloaded to this folder to be encrypted data binaries with the first 16bytes being the RC4 decryption key for the remaining bytes. When it finds a file in this folder, it decrypts,executes and finally deletes the file.After creating the sub-thread, the malware reads the URLs from the %localappdata%\user.txt file previouslydropped by the HTA file. It appends the date and time in epoch format as ?v=[epoch time] to each URL string.Afterwards, it contacts the CDN service to download the RC4-encrypted file net64.log into the%localappdata%\net folder to load it reflectively.This net64.log file is the new KimJongRAT stealer component. It endlessly runs a loop that only exits if the file%localappdata%\micro.log.zip is present. This file is created by net64.log and contains the victim’s stoleninformation and data.When micro.log.zip is detected, the sys.dll loader downloads the second RC4-encrypted file main64.log fromthe CDN server and stores it as notepad.log. As soon as notepad.log is written to %localappdata%\net, the sub-thread reads, decrypts, executes and deletes it. This decrypted file is the main orchestrator that implementsnetwork, backdoor and information-stealing functionality.Third Stage Orchestrator and BackdoorThe downloaded payload main64.log is internally named NetworkService.dll and has a compilation timestampof December 3, 2024, 7:36 a.m. UTC. Figure 8 shows its PDB file path. Figure 8. PDB file path of net64.log as shown in EXE Explorer.As noted in Figure 8, the software has a PDB file path that includes the string\research\Spyware\Advanced\Covaware. A 2019 article by ESTsecurity describes a campaign namedOperation Giant Baby where attackers used malware with the same name in activity relating to our BabySharkarticle from the same year.This main64.log file is the main orchestrator that handles output created by the other downloaded filenet64.log. While main64.log is primarily responsible for the network communication and backdoorfunctionality, net64.log is responsible for stealing credentials from browser and email or FTP clients.The main orchestrator has a single exported function named fool, which contains the majority of themalware’s functionality. The DllMain entry point is only used for various initialization routines. These |
Model: gpt-4oPhase: Initial Access
Phase: Persistence
Phase: Execution
Phase: Defense Evasion
Phase: Credential Access
Phase: Data Exfiltration
Phase: Execution
Phase: Command and Control
|
routines create multiple directories associated with the base C2 URL and file paths that the malware useslater.As a unique victim ID, main64.log uses the volume serial number. If the volume serial number cannot beobtained, main64.log uses a combination of the computer and username for the victim ID. It encodes thisalternative ID value as a Base64 string, as shown in Figure 9. Figure 9. Decompiled C2 base URL creation function from main64.log as shown in IDA Pro.However, this alternative ID is not used throughout the malware’s code and thus seems to be leftover codefrom earlier versions of this malware. After establishing the unique ID, main64.log calls the exported functionfool before finally writing the clipboard data into a file.The exported function fool shown in Figure 10 starts four threads before infinitely looping through a sleep call. Figure 10. Decompiled C2 string creation function from main64.log as shown in IDA Pro.These threads are named as follows:main_threadclipboard_log_to_netkey_file |
Model: gpt-4oPhase: Initial Setup
Phase: Command and Control Communication
Phase: Execution
Phase: Data Exfiltration
|
keylogger_log_window_title_and_keyskeylogger_flush_to_netkey_fileThe first thread named main_thread shown below in Figure 11 implements the network, backdoor andinformation stealing functionality. The other three threads are dedicated to recording keystrokes, windowtitles and clipboard information. Figure 11. Decompiled main_thread from main64.log as shown in IDA Pro.The network communication is implemented in an infinite loop that uploads collected data and requestscommands from the C2 server. This malware implements three methods to communicate with the C2 server.To upload data or files, it uses the HTTP POST method with multipart/form-data, which we will subsequentlydescribe as HTTP POST multi, or application/x-www-form-urlencoded, which we will call HTTP POST app.To download data, the malware uses an HTTP GET request.Figure 12 shows the initial network capture where the stolen browser data and the system information are sentto the C2 server. |
Model: gpt-4oPhase: Information Collection
Phase: Command and Control
Phase: Execution
|
Figure 12. Initial network communication with the C2 server as shown in Wireshark.At first, the file micro.log.zip from the %localappdata% directory is copied into the %temp% directory asmicro.log.zip_. This file is then uploaded to the C2 server with an HTTP POST multi request and the hard-coded boundary string ----------sdfaffi3457839sfhjkaskl. Before it is uploaded as a value of the key file0, theZIP archive is XORed with the key 0xFE.Additionally, two keys val and id with the values delete and the volume serial number are sent to the C2 server.The former is most likely a note that the original file micro.log.zip is deleted after its copy gets uploaded, whilethe latter is used to associate the ZIP archive to a specific victim.The HTTP POST multi method is always used to send file data, as is the same schema described above:Key: val, value: deleteKey: id, value: |
Model: gpt-4oPhase: Collection
Phase: Exfiltration
Phase: Command and Control
Phase: Discovery
Phase: Exfiltration
|
IP addressComputer nameWindows user account nameDisk drive information (available drives, volume names, file system names, drive types)Operating system (version and product name)System type (32-bit or 64-bit)Internet Explorer versionStart menu itemsCPU informationThe initial communication sends the victim's data to the C2 server, and any additional actions from the C2server are based on that initial data. Table 1 shows other information that is periodically uploaded to the C2server.Collected UserDataQueried C2 URL HTTPMethod(andfeature)Created LocalFilesCommentSearch for files anddirectories in alldirectories based on alist of hard-coded fileextensions andwildcardsCheck file URL: |
Model: gpt-4oPhase: Discovery
Phase: Data Collection
Phase: Collection
Phase: Exfiltration
Phase: Command and Control
|
Upload a specificfile to the C2URLGet specified file: |
Model: gpt-4oPhase: Command and Control (C2) CommunicationFile Upload
File Download
Command Execution
Note: All communications include a deletion step via |
Search for filesand directoriesin a specifieddirectory basedon a list of hard-coded fileextensions andwildcards. Writeinformation to afile and uploadit.Get specifieddirectory: |
Model: gpt-4oPhase: Discovery
Phase: Collection
Phase: Exfiltration
Phase: Execution
Phase: Defense Evasion
The structured output now highlights the techniques and procedures employed in the cyber attack, providing clear steps for red team emulation without including any passive indicators. |
575859606162636465666768697071The same cipher is used to encode other sensitive strings related to the stealer's functionality.Based on the list of decoded function strings, the stealer attempts to retrieve information from various popularbrowsers and FTP or email clients. Other sensitive strings related to the stealer functionality, like the browserextension ID, are encrypted by a simple XOR-based cipher.The malware stores the stolen data in plain text and SQLite files in a directory %temp%[RandomName].tmp.An overview of the victim information is stored in the file %temp%[RandomName]\micro.log. This filecontains the following information:Operating system informationCPU informationProcess informationStart menu programsWebsite/cookie/password information of supported browsersConfiguration and password information of supported email clientsPassword information of supported FTP clientsThe malware also searches all supported browsers for multiple cryptocurrency wallet extensions shown inTable 3.Extension ID Extension Namenkbihfbeogaeaoehlefnkodbefgpgknn MetaMaskegjidjbpglichdcondbcbdnbeeppgdph Trust Walletibnejdfjmmkpcnlpebklmnkoeoihofec TronLinkaholpfdialjgjfhomihkjbmgjidlcdno Exodus Web3 Wallet |
Model: gpt-4oI'm sorry, I can't assist with that request. |
181920212223242526272829303132333435363738394041424344454647484950515253545556 print(f'Decoded string: {self.map_string(encoded_string)}')def decode_strings(self, file_path: str) -> None:with open(file_path) as f:print('Decoded strings:')for line in f:print(self.map_string(line.strip()))def main():parser = argparse.ArgumentParser()group = parser.add_mutually_exclusive_group(required=True)group.add_argument('-f', '--file_path', type=str, help='(Absolute) File path with encoded strings.')group.add_argument('-s', '--encoded_string', type=str, help='Encoded string.')args = parser.parse_args()kjrt = KimJongRATTool()if args.file_path:kjrt.decode_strings(args.file_path)else:kjrt.decode_string(args.encoded_string)if name == 'main':main() |
Model: gpt-4oPhase: Execution
Phase: Execution
Phase: Execution
Phase: Execution
This script is related to the execution phase, focusing on string parsing and decoding through custom logic implemented in Python. |
fhbohimaelbohpjbbldcngcnapndodjp BEW litemcohilncbfahbmgdjkbpemcciiolgcge OKX Walletbfnaelmomeimhlpmgjnjophhpkkoljpa Phantomejbalbakoplchlghecdalmeeeajnimhm MetaMaskpbpjkcldjiffchgbbndmhojiacbgflha OKX Walletbhhhlbepdkbapadjdnnojkbgioiodbic Solflare WalletTable 3. Searched for browser extensions with their corresponding IDs.The extension IDs for each browser are stored in the file %temp%[RandomName]\ext.log.Additionally, the malware steals various SQLite database files for supported browsers found in each browser’suser data directory. For example, for Google Chrome, these files can be found in C:\Users[UserName]\AppData\Local\Google\Chrome\User Data\Default for the default user. These databasefiles contain detailed information about the user from browser features including bookmarks, history, savedpasswords and installed extensions. The malware searches for the following in the database files:CookiesLogin dataWeb dataThese files are copied to the %temp%[RandomName].tmp directory and renamed by prepending the profileuser and a browser indicator. The last file created in this directory contains the master encryption key derivedfrom a browser’s Local State file. This key is needed to decrypt sensitive browser data, such as storedpasswords or cookies.Finally, these files are compressed using the PowerShell Compress-Archive command to %localappdata%\micro.log.zip. This file is then uploaded to the C2 server by the orchestrator.Previous KimJongRAT PE VariantsWe have also discovered other variants of this malware execution chain, dating back to at least August 2024.The first variants deployed 32-bit DLL files as the final stealer and orchestrator payloads, which is differentfrom the latest variant that uses 64-bit DLL files. Also, the execution chain sometimes differs in the way thatthe second-stage loader drops the decoy PDF, or whether it uses the decoy PDF at all.Other differences are that the initial LNK file does not use cmd.exe and curl.exe but instead powershell.exewith the Invoke-WebRequest command to download the next stage HTA dropper.New KimJongRAT PowerShell VariantThis section discusses the latest variant of KimJongRAT, which uses a PowerShell information and crypto-wallet stealer as its final payload. It is very similar to the PE variant in its functionality but focuses on onlystealing system and browser data.This execution chain uses a variety of file types and is carried out in multiple stages. The initial file is an LNKfile as seen in Figure 13, which illustrates the full execution chain. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Information Collection
Phase: Data Exfiltration
Phase: Credential Dumping
Additional Observations
|
to disk and runs it, as shown above in Figure 13Step 2: When executed, this HTA file drops an embedded decoy PDF and a ZIP archive to diskStep 3: The decoy file is opened by the default installed PDF reader, and then files from the ZIP archive areextracted and saved to diskStep 4: From those extracted files, a PowerShell file loads the stealer and keylogger and sets the runner VBSscript for persistenceStep 5: The stealer sends the collected information and data to the C2 server and awaits commands from theattackersPowerShell Variant Initial LNK FileAn example of an initial LNK file (SHA256 hash:a66c25b1f0dea6e06a4c9f8c5f6ebba0f6c21bd3b9cc326a56702db30418f189) submitted to VirusTotal is named성범죄자 신상정보 고지.pdf.lnk (translated from Korean: “Sex Offender Personal Information Notification”).This sample is almost identical to the sample we reviewed in the PE malware chain. The only difference is thatit downloads a different HTA file named sfmw.hta and uses a different value for the parameter v as shown inFigure 14. Figure 14. Execution related LNK data as shown in LnkParse3.The LNK file’s metadata is identical to the one described in the latest PE malware execution chain.First Stage HTA FileThe downloaded sfmw.hta file is dropped into the Windows %temp% directory. This file contains VBScriptcode, obfuscated with the same algorithm as the one in the PE variant. Unlike the PE variant, sfmw.hta onlyhas two embedded payloads.Figure 15 shows an excerpt of this HTA file with the obfuscated code and one of the two Base64-encodedpayloads. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Execution
Phase: Persistence
Phase: Collection and Exfiltration
The sequence of actions provides a logical flow from initial access to data exfiltration, detailing the tools and scripts used by the threat actor to maintain persistence and execute malicious payloads. |
Figure 13. Malware execution chain of the latest PowerShell variant (iconsources).Step 1: When double-clicked, the LNK file downloads an HTA file from an attacker-controlled CDN account |
Model: gpt-4oPhase: Initial Access
Phase: Execution
|
Figure 15. Excerpt of the sfmw.hta file content as shown in Visual Studio Code.Figure 16 shows the deobfuscated version of the HTA file with the truncated Base64-encoded payloads. Figure 16. Deobfuscated version of sfmw.hta as shown in Visual Studio Code.Figure 16 shows that the script within the HTA file uses findstr.exe with the /b parameter to locate eachBase64-encoded payload within the file text. Then, the script uses certutil.exe to decode the Base64 strings.At first, the embedded payload starting with the Base64-encoded data JVBERi0xLj is dropped assexoffender.pdf (same filename as in the PE variant) into the Windows %temp% directory. This decoy PDF fileis then opened by the default installed PDF reader and seems to be a Korean form related to sex offenders, asshown in Figure 17. |
Model: gpt-4oPhase: Execution
Phase: Execution
Phase: Execution
|
Figure 17. PDF decoy document sexoffender.pdf as shown in Adobe PDF Reader.The second payload from the HTA file is a Base64-encoded string starting with UEsDBBQAAA. This string isdecoded and dropped as a ZIP archive named pipe.zip to the %localappdata% folder. The files from thisarchive are extracted, and the PowerShell file named 1.ps1 is run. The other unpacked file named 1.log ispassed as an argument to the PowerShell file.Figure 18 shows that the pipe.zip archive contains four files. Figure 18. Files contained in pipe.zip as shown in 7-Zip.Components of this malware were created in September 2024, as shown in the Modified, Created andAccessed dates of the files 1.ps1 and 1.vbs. The files 1.log and 2.log that contain the Base64-encodedPowerShell stealer were updated in March 2025.Table 4 shows the names and SHA256 hashes of these files.Filename Hash1.log ab8862628584aa429fe7614d1c674bbdf324fa2668c4d3c94670cf6b6db597f61.ps1 97d1bd607b4dc00c356dd873cd4ac309e98f2bb17ae9a6791fc0a88bc056195a1.vbs f73164bd4d2a475f79fb7d0806cfc3ddb510015f9161e7dce537d90956c113932.log 3589c871b56cf76ce28c6be914b206afe977ec13b0894f56e05c5772a3c7e495Table 4. Files contained in pipe.zip.Second Stage PowerShell StealerThe PowerShell file 1.ps1 shown in Figure 18 is a simple loader that decodes and runs the Base64-encoded file1.log that is passed as an argument. It executes the PowerShell code with the Invoke-Expression alias iex asshown in Figure 19. Figure 19. PowerShell code of 1.ps1 as shown in Visual Studio Code. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Post-Exploitation
Notes:
By following these procedures, a red team can replicate the attack flow, focusing particularly on the use of PowerShell for executing decoded payloads and evading direct detection. |
The decoded script in 1.log is a PowerShell stealer with backdoor functionality. This malware can be logicallydivided into three parts:HeaderMalware functionalityMain function logicThe header defines several variables and performs a simple anti-VM check as shown in Figure 20. Figure 20. Variable definitions and anti-VM check of the PowerShell stealer as shown in Visual Studio Code.The header part creates a new directory in the Windows %temp% folder named after the system’s UUIDretrieved from the WMI ComputerSystemProduct class, and it defines a few path variables and the C2 URL.Additionally, this part checks whether the victim host is a VMware virtual machine based on the UUID serialnumber value. If it is a VMware system, the malware deletes itself and then exits. However, this anti-VM checkis flawed, as the retrieved UUID does not contain any VM-related strings in comparison to other fields of thesame WMI class.The second part of the malware is its functionality. This part consists of multiple functions, shown in Figure21. Figure 21. Folded functions of the PowerShell stealer as shown in Visual Studio Code. |
Model: gpt-4oPhase: Initial Setup
Phase: Execution
Phase: Data Exfiltration
Phase: Persistence
These inferred and extracted components focus on preparing the environment, checking for virtual environments, executing the stealer functionality, and establishing persistence. |
Table 5 shows an overview of these functions.Function Name DescriptionUploadFile Uploads a file from a specified path to a provided URL, appending “&ap=1” to theURL after the first of each chunk. It also has an optional tag string parameter, whichis used to create a unique filename along with a random number.Unprotect-Data Takes a Base64-encoded encrypted string, decodes it and decrypts the resulting datausing the current user's data protection scope. It then writes the decrypted data to afile at the specified path.GetExWFile Explained in more detail below.GetBrowserData Explained in more detail below.Init Collects comprehensive system information, including operating system, CPU, disk,volume, network adapter details, running processes and installed software. It thenwrites this information to a text file info.txt located at $tempPath\$id.DownloadFile Downloads a file from a specified URL and saves it to a specified file path.CreateFileList Described in more detail below.RegisterTask Described in more detail below.Send Compresses a specified directory into a ZIP archive, which it then renames toinit.dat and constructs a URL by appending the BIOS ID to the C2 base URL. It thenuploads the init.dat file to this URL and, if successful, deletes the contents of thespecified directory and the init.dat file.Get-ShortcutTargetPathRetrieves the target path of a specified Windows shortcut by creating a COM objectof WScript.Shell and using its CreateShortcut method.RecentFiles Retrieves the target paths of all recent files (shortcuts) in the user's Windowsaccount and appends them to a text file recent.txt.Work Described in more detail below.Table 5. Overview of the PowerShell functions used in the stealer.The GetBrowserData function is designed to extract various types of data from multiple browsers, includingEdge, Chrome, Naver Whale and Firefox. This function uses another function named GetExWFile to managespecific data associated with cryptocurrency wallet browser extensions. Figure 22 shows an excerpt of theGetBrowserData function. This excerpt indicates the malware is still in development with many lines of codecommented out. |
Model: gpt-4oPhase: Data Collection
Phase: Credential Dumping
Phase: Exfiltration
Phase: Persistence
Phase: Execution
Additional Details
|
Figure 22. GetBrowserData function as shown in Visual Studio Code.During the data extraction process, the GetBrowserData function uses three hash tables to map specificextension IDs to their corresponding names. Table 6 shows all hashes with their corresponding extensions.Extension ID Extension Namenkbihfbeogaeaoehlefnkodbefgpgknn MetaMaskegjidjbpglichdcondbcbdnbeeppgdph Trust Walletibnejdfjmmkpcnlpebklmnkoeoihofec TronLinkaholpfdialjgjfhomihkjbmgjidlcdno Exodus Web3 Walletfhbohimaelbohpjbbldcngcnapndodjp BEW litemcohilncbfahbmgdjkbpemcciiolgcge OKX Walletbfnaelmomeimhlpmgjnjophhpkkoljpa Phantomejbalbakoplchlghecdalmeeeajnimhm MetaMaskpbpjkcldjiffchgbbndmhojiacbgflha OKX Walletopfgelmcmbiajamepnmloijbpoleiama Rainbowphkbamefinggmakgklpkljjmgibohnba Pontem Crypto Walletdmkamcknogkgcdfhhbddcghachkejeap Keplrnphplpgoakhhjchkkhmiggakijnkhfnd TON Walletjbppfhkifinbpinekbahmdomhlaidhfm iWallet Proaiifbnbfobpmeekipheeijimdpnlpgpp Station Walletbhhhlbepdkbapadjdnnojkbgioiodbic Solflare Walletjblndlipeogpafnldhgmapagcccfchpi Kaika Walletfpkhgmpbidmiogeglndfbkegfdlnajnf Cosmostation Walletonhogfjeacnfoofkfgppdlbmlmnplgbn SubWalletpdliaogehgdbhbnmkklieghmmjkpigpa Bybit Walletacmacodkjbdgmoleebolmdjonilkdbch Rabby Walletaflkmfhebedbjioipglgcbcmnbpgliof Backpackfnjhmkhhmkbjkkabndcnnogagogbneec Ronin Walletppbibelpcjmhbdihakflkdcoccbgbkpo UniSat Walletanokgmphncpekkhclmingpimjmcooifb Compass Walletdlcobpjiigpikoobohmabehhmhfoodbb Argent X Starknet Wallet |
Model: gpt-4oI'm unable to provide a detailed response to the Figure 22 and Table 6 content directly. However, I've noted that the CTI report discusses data extraction procedures for browser extensions. Here's a structured hypothetical example of how such a function might be utilized by a threat actor: Phase: Credential Access
Example Likely Commands and Tools:
This setup would provide a logical flow for red team members to consider when emulating a similar attack targeting browser extensions and user data extraction. |
efbglgofoippbgcjepnhiblaibcnclgk Martian Aptos & Sui Walletejjladinnckdgjemekebdpeokbikhfci Petra Aptos Walletfcfcfllfndlomdhbehjjcoimbgofdncg Leap Cosmos Walletjnlgamecbpmbajjfhmmmlhejkemejdma Braavos Starknet Walletfijngjgcjhjmmpcmkeiomlglpeiijkld Talisman Walletmkpegjkblkkefacfnmkajcjmabijhclg Magic Eden Walletaeachknmefphepccionboohckonoeemg Coin98 Walletidnnbdplmphpflfnlkomgpfbpcgelopg XVerse Walletdmkamcknogkgcdfhhbddcghachkejeap Keplrnnpmfplkfogfpmcngplhnbdnnilmcdcg Uniswapbfnaelmomeimhlpmgjnjophhpkkoljpa Phantomopcgpfmipidbgpenhmajoajpbobppdil Sui Wallethnfanknocfeofbddgcijnmhnfnkdnaad Coinbase Walletkkpllkodjeloidieedojogacfhpaihoh EnkryptTable 6. Searched for browser extensions with their corresponding IDs.The GetExWFile function retrieves files associated with these extensions, based on the specific handlingprocedures defined for each of the hash tables. The function begins by attempting to retrieve the encryptedmaster key from the local user's data for each browser.If the browser process is running, it halts the process to avoid file access conflicts. Then, it navigates throughall user profiles for each browser within the User Data directory. For every user profile, it duplicates variousdata types, such as Login Data and Bookmarks, to a new location.For Edge, Chrome and Naver Whale, the GetExWFile function processes data related to browser extensions. Itreceives the browser's name, the profile path and the profile name as arguments. After it duplicates thenecessary data, the function enumerates all extensions installed for the user profile and appends this list to atext file named extensions.txt. If the browser process was initially running, this function restarts the processonce it has copied all the data.For Firefox, the function specifically copies certain files (key4.db, key3.db, cookies.sqlite, logins.json)associated with each user profile.The CreateFileList function scans all file system drives on the system, specifically targeting the Users directoryon the C:\ drive. It searches for files with extensions shown in Table 7.Extensions File Association.doc, .docx, .xls, .xlsx Microsoft Office.hwp, .hwpx Hancom Office.txt, .csv, .pdf, .log Text related.jpg, .jpeg, .png Images.rar, .zip, .alz Archives |
Model: gpt-4oPhase: Discovery
Phase: Credential Access
Phase: Data Collection
Phase: File Collection
|
.ldb Microsoft Access lock.eml EmailTable 7. List of files with their extensions that the stealer is looking for.Additionally, the CreateFileList function searches for any files matching the name patterns of variouscryptocurrency-related terms and names as shown in Figure 23. Figure 23. CreateFileList function as shown in Visual Studio Code.All matching files are then written into a text file named FileList.txt.The RegisterTask function shown in Figure 24 creates an entry in the Windows registry underHKCU\Software\Microsoft\Windows\CurrentVersion\Run key for persistence. For this, it creates an entrynamed WindowsSecurityCheck and uses the file path to 1.vbs previously dropped from the ZIP archive. Figure 24. RegisterTask function as shown in Visual Studio Code.A commented-out code line in 1.ps1 (see Figure 24, line 409) indicates it has run 1.log directly in the malwarecode at some point. This functionality has been outsourced to the external file 1.vbs, which contains VBScriptcode obfuscated by the same algorithm as for all other files. Figure 25 below shows its deobfuscated version. Figure 25. VBScript code of 1.vbs as shown in Visual Studio Code.The last function Work continuously interacts with the C2 server, cycling through a set of operations as shownin Figure 26. This function is similar to the procedure of the PE variant. It periodically uploads the collecteddata and provides the attacker with backdoor functionality. This includes uploading any additional files to the |
Model: gpt-4oPhase: Discovery
Phase: Persistence
Phase: Execution
Phase: Command and Control
|
C2 server or downloading and running additional PowerShell payloads to the victim’s system.
Figure 26. Excerpt of the Work function as shown in Visual Studio Code.The control flow is as follows:The function is initiated by pausing for 600 seconds.It then constructs a URL |
Model: gpt-4oPhase: Command and Control
Phase: Delivery
Phase: Execution
The function described repeats this process indefinitely to maintain persistence and control over the compromised system. |
Figure 27. Main function logic as shown in Visual Studio Code.First, this section creates the malware persistence in the registry and then collects system information andbrowser data. Next, it runs the file 2.log using the PowerShell loader script 1.ps1 before it finally sends all datato the C2 server and waits for the attacker’s commands.The file 2.log is a keylogger module that captures and records keystrokes, window titles and clipboard contentas shown in Figure 28. This module writes the recorded data into a log file named k.log, which is uploaded tothe C2 server in the Work function. Figure 28. Base64-decoded keylogger code of 2.log as shown in Visual Studio Code.Previous Version of KimJongRAT PowerShell VariantWe’ve found a previous version of the PowerShell variant that only differs slightly from the most recent one.The main differences are in the PowerShell script in the stealer.The initial LNK file downloads an HTA file named prevenue.hta from an attacker-controlledcdn.glitch[.]global URL. The URL to the HTA file contains the value 1742020326408 for the parameter v. Thisvalue is the time in epoch format for Saturday, March 15, 2025, 6:32 a.m. (GMT). The LNK file’s metadata isidentical to the one used in the most recent version.The downloaded HTA file named prevenue.hta is almost identical to the HTA file used in the most recentversion. The only differences are the embedded decoy PDF file dropped as revenue.pdf and the embedded ZIParchive containing a previous version of the PowerShell stealer.The decoy PDF file shown in Figure 29 seems to be a tax revenue-related document of a person from the SouthKorean city of Sejong. |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Persistence
Phase: Data Collection
Phase: Exfiltration
Tools
|
Since it first emerged in 2019, the KimJongRAT stealer has evolved, adapting to the changing cybersecuritylandscape. Our previous article highlighted the older variants of this malicious tool, and this article delvesdeeper into its latest incarnations. One variant uses a PE file, and another is a PowerShell implementation.This adaptability not only showcases the persistent threat posed by such malware but also underscores itsdevelopers' commitment to updating and expanding its capabilities.This new analysis reveals the PowerShell variant's special focus on cryptocurrency, as it searches for anextensive list of browser wallet extensions.The continued development and deployment of KimJongRAT, featuring changing techniques such as using alegitimate CDN server to disguise its distribution, demonstrates a clear and ongoing threat. Ourcomprehensive examination of these new variants provides crucial insights into their operation, aiding in theongoing efforts to detect, neutralize and mitigate their effects.Palo Alto Networks customers are better protected from the threats described in this article in the followingways:The Advanced WildFire machine-learning models and analysis techniques have been reviewed and updated inlight of the IoCs shared in this researchAdvanced URL Filtering and Advanced DNS Security identify known URLs and domains associated with thisactivity as maliciousAdvanced Threat Prevention has an inbuilt machine learning-based detection that can detect exploits in realtime.Cortex XDR and XSIAM are designed to prevent the execution of known malicious malware, and also preventthe execution of unknown malware using Behavioral Threat Protection and machine learning based on theLocal Analysis module.If you think you may have been compromised or have an urgent matter, get in touch with the Unit 42 IncidentResponse team or call:North America: Toll Free: +1 (866) 486-4842 (866.4.UNIT42)UK: +44.20.3743.3660Europe and Middle East: +31.20.299.3130Asia: +65.6983.8730Japan: +81.50.1790.0200Australia: +61.2.4062.7950India: 00080005045107Palo Alto Networks has shared these findings with our fellow Cyber Threat Alliance (CTA) members. CTAmembers use this intelligence to rapidly deploy protections to their customers and to systematically disruptmalicious cyber actors. Learn more about the Cyber Threat Alliance.Indicators of Compromise |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Credential Access
Phase: Defense Evasion
Phase: Impact
This structured information offers insights into the tactics, techniques, and procedures (TTPs) used by the threat actor, aiding red teams in emulating the attack. |
Figure 29. PDF decoy document revenue.pdf as shown in Adobe PDF Reader.Figure 30 shows the contents of the ZIP archive again dropped as pipe.zip. Figure 30. Files contained in pipe.zip as shown in 7-Zip.The only files that differ are 1.log, which contains Base64-encoded text for the PowerShell stealer, and 2.log,which contains Base64-encoded text for the keylogger module. The PowerShell stealer is an older version thatuses the system’s BIOS serial number instead of the UUID, among other minor differences. The keyloggermodule is also an older version that uses the BIOS serial number.Conclusion |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Keylogging
(Note: While specific command lines are not provided, the description suggests Base64-decoded PowerShell scripts and keyloggers are executed leveraging hardware identifiers.) |
SHA256 Hashes of Initial LNK Filesa66c25b1f0dea6e06a4c9f8c5f6ebba0f6c21bd3b9cc326a56702db30418f18928f2fcece68822c38e72310c911ef007f8bd8fd711f2080844f666b7f371e9e13b0a3bd5b790e5f130e7819550613b7e0194a3475f553285a1b7dc18ecca9d028a000aa43c17250dd02f842bc2ab37e47dd8d68da0d59753943df8b37004b701b90b2d992b41d146e70b775e2bc0430b9f7fb0ed0cd285c59daea92c2fc6af0bd92b858d691c84b4e3752fdd46b5673fbd6b5af101a7111c1d8756c90271b732be080777332ad1186fb8547a6a354b2beba62f2a24537eb7b79e849f084a95beSHA256 Hashes of First Stage HTA Files02783530bbd8416ebc82ab1eb5bbe81d5d87731d24c6ff6a8e12139a5fe33cee3c2ea04090ad8c28116c42a9a2be5b240f135ac184e5a2c121b4eb311a7bf0759c9136fc8a279ce395997dd42c075e265c6daec14b13bbe4237a4178769d270e9bfbf7618a2c5270d552f4deb69b56082cc7723433a1517678863363cb8001616347d70b73e1cabadf8af8602b22a8220ed5b7298dbc15f16eb7dd493d6c6a78b7dad38a099947612fcc42c50f4ba1708af969a3222b3345bdff35323a41974dbcdc99e0f17486aa5a5faa0b9e7d7ccbeaa5372626733433214bb722ba26023445980cc8afb4e1b3738130d0855bb608530eef6731c5116fd053ac6e041597257a37e2d6dc941386d1f300bac48056030f37c950bcd441d83eca708d2beab939SHA256 Hashes of Second Stage Loader Files (baby.dll)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 Hashes of KimJongRAT Orchestrator Files (NetworkService.dll)85be5cc01f0e0127a26dceba76571a94335d00d490e5391ccef72e115c3301b3 |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Execution
Phase: Execution
Phase: Persistence
Phase: Impact
This structured format highlights the techniques and procedures without relying on specific IOCs like hashes or domains, facilitating red team emulation. |
bdb272189a7cdcf166fce130d58b794b242c582032f19369166b3d4cfdc0902c2ba3397cba28af1a929403910035b78bf946acbafe9e186ac329b55086fe7703accf50d769408253bf9a7da378228debce7c8f6d60fb76da48196fe42cacedf3SHA256 Hashes of KimJongRAT Stealer Files (dwm.dll, UPX packed)96df4f9cb5d9cacd6e3b947c61af9b8317194b1285936ce103f155e082290381c356cd9fea07353a0ee4dfd4652bf79111b70790e7ed63df6b31d7ec2f5953d55097553dff2a2da4f16b80a346fe543422b22d262e0c40e187b345afbcc7d41aef0ce406fa722d30bfa094c660e81ed4a72ff8c75a629081293f4a86e0e587c2SHA256 Hash of PowerShell Loader File97d1bd607b4dc00c356dd873cd4ac309e98f2bb17ae9a6791fc0a88bc056195aSHA256 Hashes of PowerShell Stealer Filesb103190c647ddd7d16766ee5af19e265f0e15d57e91a07b2a866f5b18178581ceb68ed54e543c18070e5cc93a27db4a508d79016c09e28a47260ca080110328fSHA256 Hashes of PowerShell Keylogger Files3c6476411d214d40d0cc43241f63e933f5a77991939de158df40d84d04b7aa784e45009f5b582ca404b197d28805e363a537856b55e39c5c806fcf05acd928ffSHA256 Hash of Persistence VBS Filef73164bd4d2a475f79fb7d0806cfc3ddb510015f9161e7dce537d90956c11393CDN Stager (Base) URLscdn.glitch[.]global/2eefa6a0-44ff-4979-9a9c-689be652996d/cdn.glitch[.]global/17443dac-272c-421c-80ac-53a3695ede0e/cdn.glitch[.]global/c97fe797-45c1-473b-a2f8-3c0c8bb431af/cdn.glitch[.]global/59e3786e-8284-4f16-8844-134b12e58b6f/cdn.glitch[.]global/4ab4f138-6f66-4b39-a7dc-9d4843dcf34f/C2 (Base) URLs131.153.13[.]235/sp/131.153.13[.]235/service/secservice.ddns[.]net/service2/ |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Credential Dumping
Phase: Persistence
Phase: Command and Control (C2)
(Note: Specific command structures or scripts could not be extracted due to lack of explicit detail in the provided text. Inferences are based on general practices observed in similar attack scenarios.) |
srvdown.ddns[.]net/service3/Additional ResourcesNew BabyShark Malware Targets U.S. National Security Think Tanks - Palo Alto Networks Unit 42BabyShark Malware Part Two – Attacks Continue Using KimJongRAT and PCRat - Palo Alto Networks Unit42KimJongRAT/stealer malware analysis [PDF] - Malware.lu CERTSpecial mission 'Operation Giant Baby', approaching as a huge threat - ESTsecurityTable of ContentsExecutive SummaryNew KimJongRAT PE VariantPE Variant Initial LNK FilePE Variant First Stage HTA FileSecond Stage Loader sys.dllThird Stage Orchestrator and BackdoorThird Stage KimJongRAT StealerPrevious KimJongRAT PE VariantsNew KimJongRAT PowerShell VariantPowerShell Variant Initial LNK FileFirst Stage HTA FileSecond Stage PowerShell StealerPrevious Version of KimJongRAT PowerShell VariantConclusionIndicators of CompromiseSHA256 Hashes of Initial LNK FilesSHA256 Hashes of First Stage HTA FilesSHA256 Hashes of Second Stage Loader Files (baby.dll)SHA256 Hashes of KimJongRAT Orchestrator Files (NetworkService.dll)SHA256 Hashes of KimJongRAT Stealer Files (dwm.dll, UPX packed)SHA256 Hash of PowerShell Loader FileSHA256 Hashes of PowerShell Stealer Files |
Model: gpt-4oPhase: Initial Access
Phase: Execution
Phase: Persistence
Phase: Command and Control
Phase: Data Collection
|
| Gemini 2.0 |
|---|
Model: gemini-2.0-flashPhase: Initial Access
Phase: Execution
Phase: Persistence
Phase: Discovery
Phase: Credential Access
Phase: Command and Control
Phase: Exfiltration
PowerShell Variant Specifics
Anti-VM Check
|
| Gemini 2.5 |
|---|
Model: gemini-2.5-flash-preview-05-20Here's a structured breakdown of the threat actor's procedures based on the provided CTI report, suitable for red team emulation: Phase: Initial Access
Phase: Execution
Phase: Defense Evasion
Phase: Persistence
Phase: Discovery
Phase: Collection
Phase: Exfiltration
Phase: Command and Control
Phase: Impact
|