ブログ
/
Network
/
February 11, 2025

Defending Against Living-off-the-Land Attacks: Anomaly Detection in Action

Discover how Darktrace detected and responded to cyberattacks using Living-off-the-Land (LOTL) tactics to exploit trusted services and tools on customer networks.
Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Alexandra Sentenac
Cyber Analyst
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
11
Feb 2025

What is living-off-the-land?

Threat actors employ a variety of techniques to compromise target networks, including exploiting unpatched vulnerabilities, abusing misconfigurations, deploying backdoors, and creating custom malware. However, these methods generate a lot of noise and are relatively easy for network and host-based monitoring tools to detect, especially once indicators of compromise (IoCs) and tactics, techniques, and procedures (TTPs) are published by the cybersecurity community.

Living-off-the-Land (LOTL) techniques, however, allow attacks to remain nearly invisible to Endpoint Detection and Response (EDR) tools – leveraging trusted protocols, applications and native systems to carry out malicious activity. While mitigations exist, they are often poorly implemented. The Cybersecurity and Infrastructure Security Agency (CISA) found that some organizations “lacked security baselines, allowing [Living-off-the-Land binaries (LOLBins)] to execute and leaving analysts unable to identify anomalous activity” and “organizations did not appropriately tune their detection tools to reduce alert noise, leading to an unmanageable level of alerts to sift through and action" [1].

Darktrace / NETWORK addresses this challenge across Information Technology (IT), Operational Technology (OT), and cloud environments by continuously analyzing network traffic and identifying deviations from normal behavior with its multi-layered AI – helping organizations detect and respond to LOTL attacks in real time.

Darktrace’s detection of LOTL attacks

This blog will review two separate attacks detected by Darktrace that leveraged LOTL techniques at several stages of the intrusion.

Case A

Reconnaissance

In September 2024, a malicious actor gained access to a customer network via their Virtual Private Network (VPN) from two desktop devices that had no prior connection history. Over two days, the attacker conducted multiple network scans, targeting ports associated with Remote Desktop Protocol (RDP) and NTLM authentication. Darktrace detected this unusual activity, triggering multiple alerts for scanning and enumeration activity.

Unusual NTLM authentication attempts using default accounts like “Guest” and “Administrator” were detected. Two days after the initial intrusion, suspicious DRSGetNCChanges requests were observed on multiple domain controllers (DCs), targeting the Directory Replication Service RPC interface (i.e., drsuapi) – a technique used to extract account hashes from DCs. This process can be automated using tools like Mimikatz's DcSync and DCShadow

Around the same time, attacker-controlled devices were seen presenting an admin credential and another credential potentially granting access to Cisco Firewall systems, suggesting successful privilege escalation. Due to the severity of this activity, Darktrace’s Autonomous Response was triggered to prevent the device from further deviation from its normal behavior. However, because Autonomous Response was configured in Human Confirmation mode, the response actions had to be manually applied by the customer.

Cyber AI Analyst Critical Incident showing the unusual DRSGetNCChanges requests following unusual scanning activity.
Figure 1: Cyber AI Analyst Critical Incident showing the unusual DRSGetNCChanges requests following unusual scanning activity.

Lateral movement

Darktrace also detected anomalous RDP connections to domain controllers, originating from an attacker-controlled device using admin and service credentials. The attacker then successfully pivoted to a likely RDP server, leveraging the RDP protocol – one of the most commonly used for lateral movement in network compromises observed by Darktrace.

Cyber Analyst Incident displaying unusual RDP lateral movement connections
Figure 2: Cyber Analyst Incident displaying unusual RDP lateral movement connections.

Tooling

Following an incoming RDP connection, one of the DCs made a successful GET request to the URI '/download/122.dll' on the 100% rare IP, 146.70.145[.]189. The request returned an executable file, which open-source intelligence (OSINT) suggests is likely a CobaltStrike C2 sever payload [2] [3]. Had Autonomous Response been enabled here, it would have blocked all outgoing traffic from the DC allowing the customer to investigate and remediate.

Additionally, Darktrace detected a suspicious CreateServiceW request to the Service Control (SVCCTL) RPC interface on a server. The request executed commands using ‘cmd.exe’ to perform the following actions

  1. Used ‘tasklist’ to filter processes named ”lsass.exe” (Local Security Authority Subsystem Service) to find its specific process ID.
  2. Used “rundll32.exe” to execute the MiniDump function from the “comsvcs.dll” library, creating a memory dump of the “lsass.exe” process.
  3. Saved the output to a PNG file in a temporary folder,

Notably, “cmd.exe” was referenced as “CMd.EXE” within the script, likely an attempt to evade detection by security tools monitoring for specific keywords and patterns.

Model Alert Log showing the unusual SVCCTL create request.
Figure 3: Model Alert Log showing the unusual SVCCTL create request.

Over the course of three days, this activity triggered around 125 Darktrace / NETWORK alerts across 11 internal devices. In addition, Cyber AI Analyst launched an autonomous investigation into the activity, analyzing and connecting 16 separate events spanning multiple stages of the cyber kill chain - from initial reconnaissance to payload retrieval and lateral movement.

Darktrace’s comprehensive detection enabled the customer’s security team to remediate the compromise before any further escalation was observed.

Case B

Between late 2023 and early 2024, Darktrace identified a widespread attack that combined insider and external threats, leveraging multiple LOTL tools for reconnaissance and lateral movement within a customer's network.

Reconnaissance

Initially, Darktrace detected the use of a new administrative credential by a device, which then made unusual RDP connections to multiple internal systems, including a 30-minute connection to a DC. Throughout the attack, multiple unusual RDP connections using the new administrative credential “%admin!!!” were observed, indicating that this protocol was leveraged for lateral movement.

The next day, a Microsoft Defender Security Integration alert was triggered on the device due to suspicious Windows Local Security Authority Subsystem Service (LSASS) credential dump behavior. Since the LSASS process memory can store operating system and domain admin credentials, obtaining this sensitive information can greatly facilitate lateral movement within a network using legitimate tools such as PsExec or Windows Management Instrumentation (WMI) [4]. Security integrations with other security vendors like this one can provide insights into host-based processes, which are typically outside of Darktrace’s coverage. Darktrace’s anomaly detection and network activity monitoring help prioritize the investigation of these alerts.

Three days later, the attacker was observed logging into the DC and querying tickets for the Lightweight Directory Access Protocol (LDAP) service using the default credential “Administrator.” This activity, considered new by Darktrace, triggered an Autonomous Response action that blocked further connections on Kerberos port 88 to the DC. LDAP provides a central location to access and manage data about computers, servers, users, groups, and policies within a network. LDAP enumeration can provide valuable Active Directory (AD) object information to an attacker, which can be used to identify critical attack paths or accounts with high privileges.

Lateral movement

Following the incoming RDP connection, the DC began scanning activities, including RDP and Server Block Message (SMB) services, suggesting the attacker was using remote access for additional reconnaissance. Outgoing RDP connection attempts to over 100 internal devices were observed, with around 5% being successful, highlighting the importance of this protocol for the threat actor’s lateral movement.

Around the same time, the DC made WMI, PsExec, and service control connections to two other DCs, indicating further lateral movement using native administrative protocols and tools. These functions can be leveraged by attackers to query system information, run malicious code, and maintain persistent access to compromised devices while avoiding traditional security tool alarms. In this case, requested services included the IWbemServices (used to access WMI services) and IWbemFetchSmartEnum (used to retrieve a network-optimized enumerator interface) interfaces, with ExecQuery operations detected for the former. This method returns an enumerable collection of IWbemClassObject interface objects based on a query.

Additionally, unusual Windows Remote Management (WinRM) connections to another domain controller were observed. WinRM is a Microsoft protocol that allows systems to exchange and access management information over HTTP(S) across a network, such as running executables or modifying the registry and services.

Cyber AI Analyst Incident showing unusual WMI activity between the two DCs.
Figure 4: Cyber AI Analyst Incident showing unusual WMI activity between the two DCs.

The DC was also detected writing the file “PSEXESVC.exe” to the “ADMIN$” share of another internal device over the SMB file transfer network protocol. This activity was flagged as highly unusual by Darktrace, as these two devices had not previously engaged in this type of SMB connectivity.

It is rare for an attacker to immediately find the information or systems they are after, making it likely they will need to move around the network before achieving their objectives. Tools such as PsExec enable attackers to do this while largely remaining under the radar. With PsExec, attackers who gain access to a single system can connect to and execute commands remotely on other internal systems, access sensitive information, and spread their attack further into the environment.

Model Alert Event Log showing the new write of the file “PSEXESVC.exe” by one of the compromised devices over an SMB connection initiated at an unusual time.
Figure 5. Model Alert Event Log showing the new write of the file “PSEXESVC.exe” by one of the compromised devices over an SMB connection initiated at an unusual time.

Darktrace further observed the DC connecting to the SVCCTL endpoint on a remote device and performing the CreateServiceW operation, which was flagged as highly unusual based on previous behavior patterns between the two devices. Additionally, new ChangeServiceConfigW operations were observed from another device.

Aside from IWbemServices requests seen on multiple devices, Darktrace also detected multiple internal devices connecting to the ITaskSchedulerService interface over DCE-RPC and performing new SchRpcRegisterTask operations, which register a task on the destination system. Attackers can exploit the task scheduler to facilitate the initial or recurring execution of malicious code by a trusted system process, often with elevated permissions. The creation of these tasks was considered new or highly unusual and triggered several anomalous ITaskScheduler activity alerts.

Conclusion

As pointed out by CISA, threat actors frequently exploit the lack of implemented controls on their target networks, as demonstrated in the incidents discussed here. In the first case, VPN access was granted to all domain users, providing the attacker with a point of entry. In the second case, there were no restrictions on the use of RDP within the targeted network segment, allowing the attackers to pivot from device to device.

Darktrace assists security teams in monitoring for unusual use of LOTL tools and protocols that can be leveraged by threat actors to achieve a wide range of objectives. Darktrace’s Self-Learning AI sifts through the network traffic noise generated by these trusted tools, which are essential to administrators and developers in their daily tasks, and highlights any anomalous and potentially unexpected use.

Credit to Alexandra Sentenac (Senior Cyber Analyst) and Ryan Traill (Analyst Content Lead)

References

[1] https://www.cisa.gov/sites/default/files/2024-02/Joint-Guidance-Identifying-and-Mitigating-LOTL_V3508c.pdf

[2] https://www.virustotal.com/gui/ip-address/146.70.145.189/community

[3] https://www.virustotal.com/gui/file/cc9a670b549d84084618267fdeea13f196e43ae5df0d88e2e18bf5aa91b97318

[4]https://www.microsoft.com/en-us/security/blog/2022/10/05/detecting-and-preventing-lsass-credential-dumping-attacks

MITRE Mapping

INITIAL ACCESS - External Remote Services

DISCOVERY - Remote System Discovery

DISCOVERY - Network Service Discovery

DISCOVERY - File and Directory Discovery

CREDENTIAL ACCESS – OS Credential Dumping: LSASS Memory

LATERAL MOVEMENT - Remote Services: Remote Desktop Protocol

LATERAL MOVEMENT - Remote Services: SMB/Windows Admin Shares

EXECUTION - System Services: Service Execution

PERSISTENCE - Scheduled Task

COMMAND AND CONTROL - Ingress Tool Transfer

Darktrace Model Detections

Case A

Device / Suspicious Network Scan Activity

Device / Network Scan

Device / ICMP Address Scan

Device / Reverse DNS Sweep

Device / Suspicious SMB Scanning Activity

Device / Possible SMB/NTLM Reconnaissance

Anomalous Connection / Unusual Admin SMB Session

Device / SMB Session Brute Force (Admin)

Device / Possible SMB/NTLM Brute Force

Device / SMB Lateral Movement

Device / Anomalous NTLM Brute Force

Anomalous Connection / SMB Enumeration

Device / SMB Session Brute Force (Non-Admin)

Device / Anomalous SMB Followed By Multiple Model Breaches

Anomalous Connection / Possible Share Enumeration Activity

Device / RDP Scan

Device / Anomalous RDP Followed By Multiple Model Breaches

Anomalous Connection / Unusual Admin RDP Session

Anomalous Connection / Active Remote Desktop Tunnel

Anomalous Connection / Anomalous DRSGetNCChanges Operation

Anomalous Connection / High Priority DRSGetNCChanges

Compliance / Default Credential Usage

User / New Admin Credentials on Client

User / New Admin Credentials on Server

Device / Large Number of Model Breaches from Critical Network Device

User / New Admin Credential Ticket Request

Compromise / Unusual SVCCTL Activity

Anomalous Connection / New or Uncommon Service Control

Anomalous File / Script from Rare External Location

Anomalous Server Activity / Anomalous External Activity from Critical Network Device

Anomalous File / EXE from Rare External Location

Anomalous File / Numeric File Download

Device / Initial Breach Chain Compromise

Device / Multiple Lateral Movement Model Breaches

Device / Large Number of Model Breaches

Compromise / Multiple Kill Chain Indicators

Case B

User / New Admin Credentials on Client

Compliance / Default Credential Usage

Anomalous Connection / SMB Enumeration

Device / Suspicious SMB Scanning Activity

Device / RDP Scan

Device / New or Uncommon WMI Activity

Device / Anomaly Indicators / New or Uncommon WMI Activity Indicator

Device / New or Unusual Remote Command Execution

Anomalous Connection / New or Uncommon Service Control

Anomalous Connection / Active Remote Desktop Tunnel

Compliance / SMB Drive Write

Anomalous Connection / Anomalous DRSGetNCChanges Operation

Device / Multiple Lateral Movement Model Breaches

Device / Anomalous ITaskScheduler Activity

Anomalous Connection / Unusual Admin RDP Session

Device / Large Number of Model Breaches from Critical Network Device

Compliance / Default Credential Usage

IOC - Type - Description/Probability

146.70.145[.]189 - IP Address - Likely C2 Infrastructure

Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Alexandra Sentenac
Cyber Analyst

More in this series

No items found.

Blog

/

Email

/

December 1, 2025

From Amazon to Louis Vuitton: How Darktrace Detects Black Friday Phishing Attacks

Default blog imageDefault blog image

Why Black Friday Drives a Surge in Phishing Attacks

In recent years, Black Friday has shifted from a single day of online retail sales and discounts to an extended ‘Black Friday Week’, often preceded by weeks of online hype. During this period, consumers are inundated with promotional emails and marketing campaigns as legitimate retailers compete for attention.

Unsurprisingly, this surge in legitimate communications creates an ideal environment for threat actors to launch targeted phishing campaigns designed to mimic legitimate retail emails. These campaigns often employ social engineering techniques that exploit urgency, exclusivity, and consumer trust in well-known brands, tactics designed to entice recipients into opening emails and clicking on malicious links.

Additionally, given the seasonal nature of Black Friday and the ever-changing habits of consumers, attackers adopt new tactics and register fresh domains each year, rather than reusing domains previously flagged as spam or phishing endpoints. While this may pose a challenge for traditional email security tools, it presents no such difficulty for Darktrace / EMAIL and its anomaly-based approach.

In the days and weeks leading up to ‘Black Friday’, Darktrace observed a spike in sophisticated phishing campaigns targeting consumers, demonstrating how attackers combine phycological manipulation with technical evasion to bypass basic security checks during this high-traffic period. This blog showcases several notable examples of highly convincing phishing emails detected and contained by Darktrace / EMAIL in mid to late November 2025.

Darktrace’s Black Friday Detections

Brand Impersonation: Deal Watchdogs’ Amazon Deals

The impersonation major online retailers has become a common tactic in retail-focused attacks, none more so than Amazon, which ranked as the fourth most impersonated brand in 2024, only behind Microsoft, Apple, Google, and Facebook [1]. Darktrace’s own research found Amazon to be the most mimicked brand, making up 80% of phishing attacks in its analysis of global consumer brands.

When faced with an email that appears to come from a trusted sender like Amazon, recipients are far more likely to engage, increasing the success rate of these phishing campaigns.

In one case observed on November 16, Darktrace detected an email with the subject line “NOW LIVE: Amazon’s Best Early Black Friday Deals on Gadgets Under $60”. The email was sent to a customer by the sender ‘Deal Watchdogs’, in what appeared to be an attempt to masquerade as a legitimate discount-finding platform. No evidence indicated that the company was legitimate. In fact, the threat actor made no attempt to create a convincing name, and the domain appeared to be generated by a domain generation algorithm (DGA), as shown in Figure 2.

Although the email was sent by ‘Deal Watchdogs’, it attempted to impersonate Amazon by featuring realistic branding, including the Amazon logo and a shade of orange similar to that used by them for the ‘CLICK HERE’ button and headline text.

Figure 1: The contents of the email observed by Darktrace, featuring authentic-looking Amazon branding.

Darktrace identified that the email, marked as urgent by the sender, contained a suspicious link to a Google storage endpoint (storage.googleapis[.]com), which had been hidden by the text “CLICK HERE”. If clicked, the link could have led to a credential harvester or served as a delivery vector for a malicious payload hosted on the Google storage platform.

Fortunately, Darktrace immediately identified the suspicious nature of this email and held it before delivery, preventing recipients from ever receiving or interacting with the malicious content.

Figure 2: Darktrace / EMAIL’s detection of the malicious phishing email sent to a customer.

Around the same time, Darktrace detected a similar email attempting to spoof Amazon on another customer’s network with the subject line “Our 10 Favorite Deals on Amazon That Started Today”, also sent by ‘Deal Watchdogs,’ suggesting a broader campaign.

Analysis revealed that this email originated from the domain petplatz[.]com, a fake marketing domain previously linked to spam activity according to open-source intelligence (OSINT) [2].

Brand Impersonation: Louis Vuitton

A few days later, on November 20, Darktrace / EMAIL detected a phishing email attempting to impersonate the luxury fashion brand Louis Vuitton. At first glance, the email, sent under the name ‘Louis Vuitton’ and titled “[Black Friday 2025] Discover Your New Favorite Louis Vuitton Bag – Elegance Starts Here”, appeared to be a legitimate Black Friday promotion. However, Darktrace’s analysis uncovered several red flags indicating a elaborate brand impersonation attempt.

The email was not sent by Louis Vuitton but by rskkqxyu@bookaaatop[.]ru, a Russia-based domain never before observed on the customer’s network. Darktrace flagged this as suspicious, noting that .ru domains were highly unusual for this recipient’s environment, further reinforcing the likelihood of malicious intent. Subsequent analysis revealed that the domain had only recently registered and was flagged as malicious by multiple OSINT sources [3].

Figure 3: Darktrace / EMAIL’s detection of the malicious email attempting to spoofLouis Vuitton, originating from a suspicious Russia-based domain.

Darktrace further noted that the email contained a highly suspicious link hidden behind the text “View Collection” and “Unsubscribe,” ensuring that any interaction, whether visiting the supposed ‘handbag store’ or attempting to opt out of marketing emails, would direct recipients to the same endpoint. The link resolved to xn--80aaae9btead2a[.]xn--p1ai (топааабоок[.]рф), a domain confirmed as malicious by multiple OSINT sources [4]. At the time of analysis, the domain was inaccessible, likely due to takedown efforts or the short-lived nature of the campaign.

Darktrace / EMAIL blocked this email before it reached customer inboxes, preventing recipients from interacting with the malicious content and averting any disruption.

Figure 4: The suspicious domain linked in the Louis Vuitton phishing email, now defunct.

Too good to be true?

Aside from spoofing well-known brands, threat actors frequently lure consumers with “too good to be true” luxury offers, a trend Darktrace observed in multiple cases throughout November.

In one instance, Darktrace identified an email with the subject line “[Black Friday 2025] Luxury Watches Starting at $250.” Emails contained a malicious phishing link, hidden behind text like “Rolex Starting from $250”, “Shop Now”, and “Unsubscribe”.

Figure 5: Example of a phishing email detected by Darktrace, containing malicious links concealed behind seemingly innocuous text.

Similarly to the Louis Vuitton email campaign described above, this malicious link led to a .ru domain (hxxps://x.wwwtopsalebooks[.]ru/.../d65fg4er[.]html), which had been flagged as malicious by multiple sources [5].

Figure 6: Darktrace / EMAIL’s detection of a malicious email promoting a fake luxury watch store, which was successfully held from recipient inboxes.

If accessed, this domain would redirect users to luxy-rox[.]com, a recently created domain (15 days old at the time of writing) that has also been flagged as malicious by OSINT sources [6]. When visited, the redirect domain displayed a convincing storefront advertising high-end watches at heavily discounted prices.

Figure 7: The fake storefront presented upon visiting the redirectdomain, luxy-rox[.]com.

Although the true intent of this domain could not be confirmed, it was likely a scam site or a credential-harvesting operation, as users were required to create an account to complete a purchase. As of the time or writing, the domain in no longer accessible .

This email illustrates a layered evasion tactic: attackers employed multiple domains, rapid domain registration, and concealed redirects to bypass detection. By leveraging luxury branding and urgency-driven discounts, the campaign sought to exploit seasonal shopping behaviors and entice victims into clicking.

Staying Protected During Seasonal Retail Scams

The investigation into these Black Friday-themed phishing emails highlights a clear trend: attackers are exploiting seasonal shopping events with highly convincing campaigns. Common tactics observed include brand impersonation (Amazon, Louis Vuitton, luxury watch brands), urgency-driven subject lines, and hidden malicious links often hosted on newly registered domains or cloud services.

These campaigns frequently use redirect chains, short-lived infrastructure, and psychological hooks like exclusivity and luxury appeal to bypass user scepticism and security filters. Organizations should remain vigilant during retail-heavy periods, reinforcing user awareness training, link inspection practices, and anomaly-based detection to mitigate these evolving threats.

Credit to Ryan Traill (Analyst Content Lead) and Owen Finn (Cyber Analyst)

Appendices

References

1.        https://keepnetlabs.com/blog/top-5-most-spoofed-brands-in-2024

2.        https://www.virustotal.com/gui/domain/petplatz.com

3.        https://www.virustotal.com/gui/domain/bookaaatop.ru

4.        https://www.virustotal.com/gui/domain/xn--80aaae9btead2a.xn--p1ai

5.        https://www.virustotal.com/gui/url/e2b868a74531cd779d8f4a0e1e610ec7f4efae7c29d8b8ab32c7a6740d770897?nocache=1

6.        https://www.virustotal.com/gui/domain/luxy-rox.com

Indicators of Compromise (IoCs)

IoC – Type – Description + Confidence

petplatz[.]com – Hostname – Spam domain

bookaaatop[.]ru – Hostname – Malicious Domain

xn--80aaae9btead2a[.]xn--p1ai (топааабоок[.]рф) – Hostname - Malicious Domain

hxxps://x.wwwtopsalebooks[.]ru/.../d65fg4er[.]html) – URL – Malicious Domain

luxy-rox[.]com – Hostname -  Malicious Domain

MITRE ATT&CK Mapping  

Tactic – Technique – Sub-Technique  

Initial Access - Phishing – (T1566)  

Continue reading
About the author
Ryan Traill
Analyst Content Lead

Blog

/

Network

/

November 27, 2025

CastleLoader & CastleRAT: Behind TAG150’s Modular Malware Delivery System

Default blog imageDefault blog image

What is TAG-150?

TAG-150, a relatively new Malware-as-a-Service (MaaS) operator, has been active since March 2025, demonstrating rapid development and an expansive, evolving infrastructure designed to support its malicious operations. The group employs two custom malware families, CastleLoader and CastleRAT, to compromise target systems, with a primary focus on the United States [1]. TAG-150’s infrastructure included numerous victim-facing components, such as IP addresses and domains functioning as command-and-control (C2) servers associated with malware families like SecTopRAT and WarmCookie, in addition to CastleLoader and CastleRAT [2].

As of May 2025, CastleLoader alone had infected a reported 469 devices, underscoring the scale and sophistication of TAG-150’s campaign [1].

What are CastleLoader and CastleRAT?

CastleLoader is a loader malware, primarily designed to download and install additional malware, enabling chain infections across compromised systems [3]. TAG-150 employs a technique known as ClickFix, which uses deceptive domains that mimic document verification systems or browser update notifications to trick victims into executing malicious scripts. Furthermore, CastleLoader leverages fake GitHub repositories that impersonate legitimate tools as a distribution method, luring unsuspecting users into downloading and installing malware on their devices [4].

CastleRAT, meanwhile, is a remote access trojan (RAT) that serves as one of the primary payloads delivered by CastleLoader. Once deployed, CastleRAT grants attackers extensive control over the compromised system, enabling capabilities such as keylogging, screen capturing, and remote shell access.

TAG-150 leverages CastleLoader as its initial delivery mechanism, with CastleRAT acting as the main payload. This two-stage attack strategy enhances the resilience and effectiveness of their operations by separating the initial infection vector from the final payload deployment.

How are they deployed?

Castleloader uses code-obfuscation methods such as dead-code insertion and packing to hinder both static and dynamic analysis. After the payload is unpacked, it connects to its command-and-control server to retrieve and running additional, targeted components.

Its modular architecture enables it to function both as a delivery mechanism and a staging utility, allowing threat actors to decouple the initial infection from payload deployment. CastleLoader typically delivers its payloads as Portable Executables (PEs) containing embedded shellcode. This shellcode activates the loader’s core module, which then connects to the C2 server to retrieve and execute the next-stage malware.[6]

Following this, attackers deploy the ClickFix technique, impersonating legitimate software distribution platforms like Google Meet or browser update notifications. These deceptive sites trick victims into copying and executing PowerShell commands, thereby initiating the infection kill chain. [1]

When a user clicks on a spoofed Cloudflare “Verification Stepprompt, a background request is sent to a PHP script on the distribution domain (e.g., /s.php?an=0). The server’s response is then automatically copied to the user’s clipboard using the ‘unsecuredCopyToClipboard()’ function. [7].

The Python-based variant of CastleRAT, known as “PyNightShade,” has been engineered with stealth in mind, showing minimal detection across antivirus platforms [2]. As illustrated in Figure 1, PyNightShade communicates with the geolocation API service ip-api[.]com, demonstrating both request and response behavior

Packet Capture (PCAP) of PyNightShade, the Python-based variant of CastleRAT, communicating with the geolocation API service ip-api[.]com.
Figure 1: Packet Capture (PCAP) of PyNightShade, the Python-based variant of CastleRAT, communicating with the geolocation API service ip-api[.]com.

Darktrace Coverage

In mid-2025, Darktrace observed a range of anomalous activities across its customer base that appeared linked to CastleLoader, including the example below from a US based organization.

The activity began on June 26, when a device on the customer’s network was observed connecting to the IP address 173.44.141[.]89, a previously unseen IP for this network along with the use of multiple user agents, which was also rare for the user.  It was later determined that the IP address was a known indicator of compromise (IoC) associated with TAG-150’s CastleRAT and CastleLoader operations [2][5].

Figure 2: Darktrace’s detection of a device making unusual connections to the malicious endpoint 173.44.141[.]89.

The device was observed downloading two scripts from this endpoint, namely ‘/service/download/data_5x.bin’ and ‘/service/download/data_6x.bin’, which have both been linked to CastleLoader infections by open-source intelligence (OSINT) [8]. The archives contains embedded shellcode, which enables attackers to execute arbitrary code directly in memory, bypassing disk writes and making detection by endpoint detection and response (EDR) tools significantly more difficult [2].

 Darktrace’s detection of two scripts from the malicious endpoint.
Figure 3: Darktrace’s detection of two scripts from the malicious endpoint.

In addition to this, the affected device exhibited a high volume of internal connections to a broad range of endpoints, indicating potential scanning activity. Such behavior is often associated with reconnaissance efforts aimed at mapping internal infrastructure.

Darktrace / NETWORK correlated these behaviors and generated an Enhanced Monitoring model, a high-fidelity security model designed to detect activity consistent with the early stages of an attack. These high-priority models are continuously monitored and triaged by Darktrace’s Security Operations Center (SOC) as part of the Managed Threat Detection and Managed Detection & Response services, ensuring that subscribed customers are promptly alerted to emerging threats.

Darktrace detected an unusual ZIP file download alongside the anomalous script, followed by internal connectivity. This activity was correlated under an Enhanced Monitoring model.
Figure 4: Darktrace detected an unusual ZIP file download alongside the anomalous script, followed by internal connectivity. This activity was correlated under an Enhanced Monitoring model.

Darktrace Autonomous Response

Fortunately, Darktrace’s Autonomous Response capability was fully configured, enabling it to take immediate action against the offending device by blocking any further connections external to the malicious endpoint, 173.44.141[.]89. Additionally, Darktrace enforced a ‘group pattern of life’ on the device, restricting its behavior to match other devices in its peer group, ensuring it could not deviate from expected activity, while also blocking connections over 443, shutting down any unwanted internal scanning.

Figure 5: Actions performed by Darktrace’s Autonomous Response to contain the ongoing attack.

Conclusion

The rise of the MaaS ecosystem, coupled with attackers’ growing ability to customize tools and techniques for specific targets, is making intrusion prevention increasingly challenging for security teams. Many threat actors now leverage modular toolkits, dynamic infrastructure, and tailored payloads to evade static defenses and exploit even minor visibility gaps. In this instance, Darktrace demonstrated its capability to counter these evolving tactics by identifying early-stage attack chain behaviors such as network scanning and the initial infection attempt. Autonomous Response then blocked the CastleLoader IP delivering the malicious ZIP payload, halting the attack before escalation and protecting the organization from a potentially damaging multi-stage compromise

Credit to Ahmed Gardezi (Cyber Analyst) Tyler Rhea (Senior Cyber Analyst)
Edited by Ryan Traill (Analyst Content Lead)

Appendices

Darktrace Model Detections

  • Anomalous Connection / Unusual Internal Connections
  • Anomalous File / Zip or Gzip from Rare External Location
  • Anomalous File / Script from Rare External Location
  • Initial Attack Chain Activity (Enhanced Monitoring Model)

MITRE ATT&CK Mapping

  • T15588.001 - Resource Development – Malware
  • TG1599 – Defence Evasion – Network Boundary Bridging
  • T1046 – Discovery – Network Service Scanning
  • T1189 – Initial Access

List of IoCs
IoC - Type - Description + Confidence

  • 173.44.141[.]89 – IP – CastleLoader C2 Infrastructure
  • 173.44.141[.]89/service/download/data_5x.bin – URI – CastleLoader Script
  • 173.44.141[.]89/service/download/data_6x.bin – URI  - CastleLoader Script
  • wsc.zip – ZIP file – Possible Payload

References

[1] - https://blog.polyswarm.io/castleloader

[2] - https://www.recordedfuture.com/research/from-castleloader-to-castlerat-tag-150-advances-operations

[3] - https://www.pcrisk.com/removal-guides/34160-castleloader-malware

[4] - https://www.scworld.com/brief/malware-loader-castleloader-targets-devices-via-fake-github-clickfix-phishing

[5] https://www.virustotal.com/gui/ip-address/173.44.141.89/community

[6] https://thehackernews.com/2025/07/castleloader-malware-infects-469.html

[7] https://www.cryptika.com/new-castleloader-attack-using-cloudflare-themed-clickfix-technique-to-infect-windows-computers/

[8] https://www.cryptika.com/castlebot-malware-as-a-service-deploys-range-of-payloads-linked-to-ransomware-attacks/

Continue reading
About the author
Your data. Our AI.
Elevate your network security with Darktrace AI