Blog
/
Network
/
November 20, 2023

Understanding and Mitigating Sectop RAT

Understand the risks posed by the Sectop remote access Trojan and how Darktrace implements strategies to enhance cybersecurity defenses.
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
Justin Torres
Cyber Analyst
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
20
Nov 2023

Introduction

As malicious actors across the threat landscape continue to look for new ways to gain unauthorized access to target networks, it is unsurprising to see Remote Access Trojans (RATs) leveraged more and more. These RATs are downloaded discretely without the target’s knowledge, typically through seemingly legitimate software downloads, and are designed to gain highly privileged network credentials, ultimately allowing attackers to have remote control over compromised devices. [1]

SectopRAT is one pertinent example of a RAT known to adopt a number of stealth functions in order to gather and exfiltrate sensitive data from its targets including passwords, cookies, autofill and history data stores in browsers, as well as cryptocurrency wallet details and system hardware information. [2]

In early 2023, Darktrace identified a resurgence of the SectopRAT across customer environments, primarily targeting educational industries located in the United States (US), Europe, the Middle East and Africa (EMEA) and Asia-Pacific (APAC) regions. Darktrace DETECT™ was able to successfully identify suspicious activity related to SectopRAT at the network level, as well as any indicators of post-compromise on customer environments that did not have Darktrace RESPOND™ in place to take autonomous preventative action.

What is SectopRAT?

First discovered in early 2019, the SectopRAT is a .NET RAT that contains information stealing capabilities. It is also known under the alias ‘ArechClient2’, and is commonly distributed through drive-by downloads of illegitimate software and utilizes malvertising, including via Google Ads, to increase the chances of it being downloaded.

The malware’s code was updated at the beginning of 2021, which led to refined and newly implemented features, including command and control (C2) communication encryption with Advanced Encryption Stanard 256 (AES256) and additional commands. SectopRAT also has a function called "BrowserLogging", ultimately sending any actions it conducts on web browsers to its C2 infrastructure. When the RAT is executed, it then connects to a Pastebin associated hostname to retrieve C2 information; the requested file reaches out to get the public IP address of the infected device. To receive commands, it connects to its C2 server primarily on port 15647, although other ports have been highlighted by open source intelligence (OSINT), which include 15678, 15649, 228 and 80. Ultimately, sensitive data data gathered from target networks is then exfiltrated to the attacker’s C2 infrastructure, typically in a JSON file [3].

Darktrace Coverage

During autonomous investigations into affected customer networks, Darktrace DETECT was able to identify SSL connections to the endpoint pastebin[.]com over port 443, followed by failed connections to one of the IPs and ports (i.e., 15647, 15648, 15649) associated with SectopRAT. This resulted in the devices breaching the ‘Compliance/Pastebin and Anomalous Connection/Multiple Failed Connections to Rare Endpoint’ models, respectively.

In some instances, Darktrace observed a higher number of attempted connections that resulted in the additional breach of the model ‘Compromise / Large Number of Suspicious Failed Connections’.

Over a period of three months, Darktrace investigated multiple instances of SectopRAT infections across multiple clients, highlighting indicators of compromise (IoCs) through related endpoints.Looking specififically at one customer’s activity which centred on January 25, 2023, one device was observed initially making suspicious connections to a Pastebin endpoint, 104.20.67[.]143, likely in an attempt to receive C2 information.

Darktrace DETECT recognized this activity as suspicious, causing the 'Compliance / Pastebin' DETECT models to breach. In response to this detection, Darktrace RESPOND took swift action against the Pastebin connections by blocking them and preventing the device from carrying out further connections with Pastebin endpoints. Darktrace RESPOND actions related to blocking Pastebin connections were commonly observed on this device throughout the course of the attack and likely represented threat actors attempting to exfiltrate sensitive data outside the network.

Darktrace UI image
Figure 1: Model breach event log highlighting the Darktrace DETECT model breach ‘Compliance / Pastebin’.

Around the same time, Darktrace observed the device making a large number of failed connections to an unusual exernal location in the Netherlands, 5.75.147[.]135, via port 15647. Darktrace recognized that this endpoint had never previously been observed on the customer’s network and that the frequency of the failed connections could be indicative of beaconing activity. Subsequent investigation into the endpoint using OSINT indicated it had links to malware, though Darktrace’s successful detection did not need to rely on this intelligence.

Darktrace model breach event log
Figure 2: Model breach event log highlighting the multiple failed connectiosn to the suspicious IP address, 5.75.147[.]135 on January 25, 2023, causing the Darktrace DETECT model ‘Anomalous Connection / Multiple Failed Connections to Rare Endpoint’ to breach.

After these initial set of breaches on January 25, the same device was observed engaging in further external connectivity roughly a month later on February 27, including additional failed connections to the IP 167.235.134[.]14 over port 15647. Once more, multiple OSINT sources revealed that this endpoint was indeed a malicious C2 endpoint.

Darktrace model breach event log 2
Figure 3: Model breach event log highlighting the multiple failed connectiosn to the suspicious IP address, 167.235.134[.]14 on February 27, 2023, causing the Darktrace DETECT model ‘Anomalous Connection / Multiple Failed Connections to Rare Endpoint’ to breach.

While the initial Darktrace coverage up to this point has highlighted the attempted C2 communication and how DETECT was able to alert on the suspicious activity, Pastebin activity was commonly observed throughout the course of this attack. As a result, when enabled in autonomous response mode, Darktrace RESPOND was able to take swift mitigative action by blocking all connections to Pastebin associated hostnames and IP addresses. These interventions by RESPOND ultimately prevented malicious actors from stealing sensitive data from Darktrace customers.

Darktrace RESPOND action list
Figure 4: A total of nine Darktrace RESPOND actions were applied against suspicious Pastebin activity during the course of the attack.

In another similar case investigated by the Darktrace, multiple devices were observed engaging in external connectivity to another malicious endpoint,  88.218.170[.]169 (AS207651 Hosting technology LTD) on port 15647.  On April 17, 2023, at 22:35:24 UTC, the breach device started making connections; of the 34 attempts, one connection was successful – this connection lasted 8 minutes and 49 seconds. Darktrace DETECT’s Self-Learning AI understood that these connections represented a deviation from the device’s usual pattern of behavior and alerted on the activity with the ‘Multiple Connections to new External TCP Port’ model.

Darktrace model breach event log
Figure 5: Model breach event log highlighting the affected device successfully connecting to the suspicious endpoint, 88.218.170[.]169.
Darktrace advanced search query
Figure 6: Advanced Search query highlighting the one successful connection to the endpoint 88.218.170[.]169 out of the 34 attempted connections.

A few days later, on April 20, 2023, at 12:33:59 (UTC) the source device connected to a Pastebin endpoint, 172.67.34[.]170 on port 443 using the SSL protocol, that had never previously be seen on the network. According to Advanced Search data, the first SSL connection lasted over two hours. In total, the device made 9 connections to pastebin[.]com and downloaded 85 KB of data from it.

Darktrace UI highlighting connections
Figure 7: Screenshot of the Darktrace UI highlighting the affected device making multiple connections to Pastebin and downloading 85 KB of data.

Within the same minute, Darktrace detected the device beginning to make a large number of failed connections to another suspicious endpoints, 34.107.84[.]7 (AS396982 GOOGLE-CLOUD-PLATFORM) via port 15647. In total the affected device was observed initiating 1,021 connections to this malicious endpoint, all occurring over the same port and resulting the failed attempts.

Darktrace advanced search query 2
Figure 8: Advanced Search query highlighting the affected device making over one thousand connections to the suspicious endpoint 34.107.84[.]7, all of which failed.

Conclusion

Ultimately, thanks to its Self-Learning AI and anomaly-based approach to threat detection, Darktrace was able to preemptively identify any suspicious activity relating to SectopRAT at the network level, as well as post-compromise activity, and bring it to the immediate attention of customer security teams.

In addition to the successful and timely detection of SectopRAT activity, when enabled in autonomous response mode Darktrace RESPOND was able to shut down suspicious connections to endpoints used by threat actors as malicious infrastructure, thus preventing successful C2 communication and potential data exfiltration.

In the face of a Remote Access Trojan, like SectopRAT, designed to steal sensitive corporate and personal information, the Darktrace suite of products is uniquely placed to offer organizations full visibility over any emerging activity on their networks and respond to it without latency, safeguarding their digital estate whilst causing minimal disruption to business operations.

Credit to Justin Torres, Cyber Analyst, Brianna Leddy, Director of Analysis

Appendices

Darktrace Model Detection:

  • Compliance / Pastebin
  • Anomalous Connection / Multiple Failed Connections to Rare Endpoint
  • Compromise / Large Number of Suspicious Failed Connections
  • Anomalous Connection / Multiple Connections to New External TCP Port

List of IoCs

IoC - Type - Description + Confidence

5.75.147[.]135 - IP - SectopRAT C2 Endpoint

5.75.149[.]1 - IP - SectopRAT C2 Endpoint

34.27.150[.]38 - IP - SectopRAT C2 Endpoint

34.89.247[.]212 - IP - SectopRAT C2 Endpoint

34.107.84[.]7 - IP - SectopRAT C2 Endpoint

34.141.16[.]89 - IP - SectopRAT C2 Endpoint

34.159.180[.]55 - IP - SectopRAT C2 Endpoint

35.198.132[.]51 - IP - SectopRAT C2 Endpoint

35.226.102[.]12 - IP - SectopRAT C2 Endpoint

35.234.79[.]173 - IP - SectopRAT C2 Endpoint

35.234.159[.]213 - IP - SectopRAT C2 Endpoint

35.242.150[.]95 - IP - SectopRAT C2 Endpoint

88.218.170[.]169 - IP - SectopRAT C2 Endpoint

162.55.188[.]246 - IP - SectopRAT C2 Endpoint

167.235.134[.]14 - IP - SectopRAT C2 Endpoint

MITRE ATT&CK Mapping

Model: Compliance / Pastebin

ID: T1537

Tactic: EXFILTRATION

Technique Name: Transfer Data to Cloud Account

Model: Anomalous Connection / Multiple Failed Connections to Rare Endpoint

ID: T1090.002

Sub technique of: T1090

Tactic: COMMAND AND CONTROL

Technique Name: External Proxy

ID: T1095

Tactic: COMMAND AND CONTROL

Technique Name: Non-Application Layer Protocol

ID: T1571

Tactic: COMMAND AND CONTROL

Technique Name: Non-Standard Port

Model: Compromise / Large Number of Suspicious Failed Connections

ID: T1571

Tactic: COMMAND AND CONTROL

Technique Name: Non-Standard Port

ID: T1583.006

Sub technique of: T1583

Tactic: RESOURCE DEVELOPMENT

Technique Name: Web Services

Model: Anomalous Connection / Multiple Connections to New External TCP Port

ID: T1095        

Tactic: COMMAND AND CONTROL    

Technique Name: Non-Application Layer Protocol

ID: T1571

Tactic: COMMAND AND CONTROL    

Technique Name: Non-Standard Port

References

1.     https://www.techtarget.com/searchsecurity/definition/RAT-remote-access-Trojan

2.     https://malpedia.caad.fkie.fraunhofer.de/details/win.sectop_rat

3.     https://threatfox.abuse.ch/browse/malware/win.sectop_rat

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
Justin Torres
Cyber Analyst

More in this series

No items found.

Blog

/

Network

/

May 5, 2026

When Trust Becomes the Attack Surface: Supply-Chain Attacks in an Era of Automation and Implicit Trust

Software supply chain attacksDefault blog imageDefault blog image

Software supply-chain attacks in 2026

Software supply-chain attacks now represent the primary threat shaping the 2026 security landscape. Rather than relying on exploits at the perimeter, attackers are targeting the connective tissue of modern engineering environments: package managers, CI/CD automation, developer systems, and even the security tools organizations inherently trust.

These incidents are not isolated cases of poisoned code. They reflect a structural shift toward abusing trusted automation and identity at ecosystem scale, where compromise propagates through systems designed for speed, not scrutiny. Ephemeral build runners, regardless of provider, represent high‑trust, low‑visibility execution zones.

The Axios compromise and the cascading Trivy campaign illustrate how quickly this abuse can move once attacker activity enters build and delivery workflows. This blog provides an overview of the latest supply chain and security tool incidents with Darktrace telemetry and defensive actions to improve organizations defensive cyber posture.

1. Why the Axios Compromise Scaled

On 31 March 2026, attackers hijacked the npm account of Axios’s lead maintainer, publishing malicious versions 1.14.1 and 0.30.4 that silently pulled in a malicious dependency, plain‑crypto‑[email protected]. Axios is a popular HTTP client for node.js and  processes 100 million weekly downloads and appears in around 80% of cloud and application environments, making this a high‑leverage breach [1].

The attack chain was simple yet effective:

  • A compromised maintainer account enabled legitimate‑looking malicious releases.
  • The poisoned dependency executed Remote Access Trojans (RATs) across Linux, macOS and Windows systems.
  • The malware beaconed to a remote command-and-control (C2) server every 60 seconds in a loop, awaiting further instructions.
  • The installer self‑cleaned by deleting malicious artifacts.

All of this matters because a single maintainer compromise was enough to project attacker access into thousands of trusted production environments without exploiting a single vulnerability.

A view from Darktrace

Multiple cases linked with the Axios compromise were identified across Darktrace’s customer base in March 2026, across both Darktrace / NETWORK and Darktrace / CLOUD deployments.

In one Darktrace / CLOUD deployment, an Azure Cloud Asset was observed establishing new external HTTP connectivity to the IP 142.11.206[.]73 on port 8000. Darktrace deemed this activity as highly anomalous for the device based on several factors, including the rarity of the endpoint across the network and the unusual combination of protocol and port for this asset. As a result, the triggering the "Anomalous Connection / Application Protocol on Uncommon Port" model was triggered in Darktrace / CLOUD. Detection was driven by environmental context rather than a known indicator at the time. Subsequent reporting later classified the destination as malicious in relation to the Axios supply‑chain compromise, reinforcing the gap that often exists between initial attacker activity and the availability of actionable intelligence. [5]

Additionally, shortly before this C2 connection, the device was observed communicating with various endpoints associated with the NPM package manager, further reinforcing the association with this attack.

Darktrace’s detection of the unusual external connection to 142.11[.]206[.]73 via port 8000.  
Figure 1: Darktrace’s detection of the unusual external connection to 142.11[.]206[.]73 via port 8000.  

Within Axios cases observed within Darktrace / NETWORK customer environments, activity generally focused on the use of newly observed cURL user agents in outbound connections to the C2 URL sfrclak[.]com/6202033, alongside the download of malicious files.

In other cases, Darktrace / NETWORK customers with Microsoft Defender for Endpoint integration received alerts flagging newly observed system executables and process launches associated with C2 communication.

A Security Integration Alert from Microsoft Defender for Endpoint associated with the Axios supply chain attack.
Figure 2: A Security Integration Alert from Microsoft Defender for Endpoint associated with the Axios supply chain attack.

2. Why Trivy bypassed security tooling trust

Between late February and March 22, 2026, the threat group TeamPCP leveraged credentials from a previous incident to insert malicious artifacts across Trivy’s distribution ecosystem, including its CI automation, release binaries, Visual Studio Code extensions, and Docker container images [2].

While public reporting has emphasized GitHub Actions, Darktrace telemetry highlights attacker execution within CI/CD runner environments, including ephemeral build runners. These execution contexts are typically granted broad trust and limited visibility, allowing malicious activity within build automation to blend into expected operational workflows, regardless of provider.

This was a coordinated multi‑phase attack:

  • 75 of 76  of trivy-action tags and all setup‑trivy tags were force‑pushed to deliver a malicious payload.
  • A malicious binary (v0.69.4) was distributed across all major distribution channels.
  • Developer machines were compromised, receiving a persistent backdoor and a self-propagating worm.
  • Secrets were exfiltrated at scale, including SSH keys, Kuberenetes tokens, database passwords, and cloud credentials across Amazon Web Service (AWS), Azure, and Google Cloud Platform (GCP).

Within Darktrace’s customer base, an AWS EC2 instance monitored by Darktrace / CLOUD  appeared to have been impacted by the Trivy attack. On March 19, the device was seen connecting to the attacker-controlled C2 server scan[.]aquasecurtiy[.]org (45.148.10[.]212), triggering the model 'Anomalous Server Activity / Outgoing from Server’ in Darktrace / CLOUD.

Despite this limited historical context, Darktrace assessed this activity as suspicious due to the rarity of the destination endpoint across the wider deployment. This resulted in the triggering of a model alert and the generation of a Cyber AI Analyst incident to further analyze and correlate the attack activity.

TeamPCP’s continued abused of GitHub Actions against security and IT tooling has also been observed more recently in Darktrace’s customer base. On April 22, an AWS asset was seen connecting to the C2 endpoint audit.checkmarx[.]cx (94.154.172[.]43). The timing of this activity suggests a potential link to a malicious Bitwarden package distributed by the threat actor, which was only available for a short timeframe on April 22. [4][3]

Figure 3: A model alert flagging unusual external connectivity from the AWS asset, as seen in Darktrace / CLOUD .

While the Trivy activity originated within build automation, the underlying failure mode mirrors later intrusions observed via management tooling. In both cases, attackers leveraged platforms designed for scale and trust to execute actions that blended into normal operational noise until downstream effects became visible.

Quest KACE: Legacy Risk, Real Impact

The Quest KACE System Management Appliance (SMA) incident reinforces that software risk is not confined to development pipelines alone. High‑trust infrastructure and management platforms are increasingly leveraged by adversaries when left unpatched or exposed to the internet.

Throughout March 2026, attackers exploited CVE 2025-32975 to authentication on outdated, internet-facing KACE appliances, gaining administrative control and pushing remote payloads into enterprise environments. Organizations still running pre-patch versions effectively handed adversaries a turnkey foothold, reaffirming a simple strategic truth: legacy management systems are now part of the supply-chain threat surface, and treating them as “low-risk utilities” is no longer defensible [3].

Within the Darktrace customer base, a potential case was identified in mid-March involving an internet-facing server that exhibited the use of a new user agent alongside unusual file downloads and unexpected external connectivity. Darktrace identified the device downloading file downloads from "216.126.225[.]156/x", "216.126.225[.]156/ct.py" and "216.126.225[.]156/n", using the user agents, "curl/8.5.0" & "Python-urllib/3.9".

The timeframe and IoCs observed point towards likely exploitation of CVE‑2025‑32975. As with earlier incidents, the activity became visible through deviations in expected system behavior rather than through advance knowledge of exploitation or attacker infrastructure. The delay between observed exploitation and its addition to the Known Exploited Vulnerabilities (KEV) catalogue underscores a recurring failure: retrospective validation cannot keep pace with adversaries operating at automation speed.

The strategic pattern: Ecosystem‑scale adversaries

The Axios and Trivy compromises are not anomalies; they are signals of a structural shift in the threat landscape. In this post-trust era, the compromise of a single maintainer, repository token, or CI/CD tag can produce large-scale blast radiuses with downstream victims numbering in the thousands. Attackers are no longer just exploiting vulnerabilities; they are exploiting infrastructure privileges, developer trust relationships, and automated build systems that the industry has generally under secured.

Supply‑chain compromise should now be treated as an assumed breach scenario, not a specialized threat class, particularly across build, integration, and management infrastructure. Organizations must operate under the assumption that compromise will occur within trusted software and automation layers, not solely at the network edge or user endpoint. Defenders should therefore expect compromise to emerge from trusted automation layers before it is labelled, validated, or widely understood.

The future of supply‑chain defense lies in continuous behavioral visibility, autonomous detection across developer and build environments, and real‑time anomaly identification.

As AI increasingly shapes software development and security operations, defenders must assume adversaries will also operate with AI in the loop. The defensive edge will come not from predicting specific compromises, but from continuously interrogating behavior across environments humans can no longer feasibly monitor at scale.

Credit to Nathaniel Jones (VP, Security & AI Strategy, FCISCO), Emma Foulger (Global Threat Research Operations Lead), Justin Torres (Senior Cyber Analyst), Tara Gould (Malware Research Lead)

Edited by Ryan Traill (Content Manager)

Appendices

References:

1)         https://www.infosecurity-magazine.com/news/hackers-hijack-axios-npm-package/

2)         https://thehackernews.com/2026/03/trivy-hack-spreads-infostealer-via.html

3)         https://thehackernews.com/2026/03/hackers-exploit-cve-2025-32975-cvss-100.html

4)         https://www.endorlabs.com/learn/shai-hulud-the-third-coming----inside-the-bitwarden-cli-2026-4-0-supply-chain-attack

5)         https://socket.dev/blog/axios-npm-package-compromised?trk=public_post_comment-text

IoCs

- 142.11.206[.]73 – IP Address – Axios supply chain C2

- sfrclak[.]com – Hostname – Axios supply chain C2

- hxxp://sfrclak[.]com:8000/6202033 - URI – Axios supply chain payload

- 45.148.10[.]212 – IP Address – Trivy supply chain C2

- scan.aquasecurtiy[.]org – Hostname - Trivy supply chain C2

- 94.154.172[.]43 – IP Address - Checkmarx/Bitwarden supply chain C2

- audit.checkmarx[.]cx – Hostname - Checkmarx/Bitwarder supply chain C2

- 216.126.225[.]156 – IP Address – Quest KACE exploitation C2

- 216.126.225[.]156/32 - URI – Possible Quest KACE exploitation payload

- 216.126.225[.]156/ct.py - URI - Possible Quest KACE exploitation payload

- 216.126.225[.]156/n - URI - Possible Quest KACE exploitation payload

- 216.126.225[.]156/x - URI - Possible Quest KACE exploitation payload

- e1ec76a0e1f48901566d53828c34b5dc – MD5 - Possible Quest KACE exploitation payload

- d3beab2e2252a13d5689e9911c2b2b2fc3a41086 – SHA1 - Possible Quest KACE exploitation payload

- ab6677fcbbb1ff4a22cc3e7355e1c36768ba30bbf5cce36f4ec7ae99f850e6c5 – SHA256 - Possible Quest KACE exploitation payload

- 83b7a106a5e810a1781e62b278909396 – MD5 - Possible Quest KACE exploitation payload

- deb4b5841eea43cb8c5777ee33ee09bf294a670d – SHA1 - Possible Quest KACE exploitation payload

- b1b2f1e36dcaa36bc587fda1ddc3cbb8e04c3df5f1e3f1341c9d2ec0b0b0ffaf – SHA256 - Possible Quest KACE exploitation payload

Darktrace Model Detections

Anomalous Connection / Application Protocol on Uncommon Port

Anomalous Server Activity / Outgoing from Server

Anomalous Connection / New User Agent to IP Without Hostname

Anomalous File / EXE from Rare External Location

Anomalous File / Script from Rare External Location

Anomalous Server Activity / New User Agent from Internet Facing System

Anomalous Server Activity / Rare External from Server

Antigena / Network / External Threat / Antigena Suspicious File Block

Antigena / Network / External Threat / Antigena Suspicious File Pattern of Life Block

Device / New User Agent

Device / Internet Facing Device with High Priority Alert

Anomalous File / New User Agent Followed By Numeric File Download

Continue reading
About the author
Nathaniel Jones
VP, Security & AI Strategy, Field CISO

Blog

/

Email

/

May 5, 2026

How email-delivered prompt injection attacks can target enterprise AI – and why it matters

Default blog imageDefault blog image

What are email-delivered prompt injection attacks?

As organizations rapidly adopt AI assistants to improve productivity, a new class of cyber risk is emerging alongside them: email-delivered AI prompt injection. Unlike traditional attacks that target software vulnerabilities or rely on social engineering, this is the act of embedding malicious or manipulative instructions into content that an AI system will process as part of its normal workflow. Because modern AI tools are designed to ingest and reason over large volumes of data, including emails, documents, and chat histories, they can unintentionally treat hidden attacker-controlled text as legitimate input.  

At Darktrace, our analysis has shown an increase of 90% in the number of customer deployments showing signals associated with potential prompt injection attempts since we began monitoring for this type of activity in late 2025. While it is not always possible to definitively attribute each instance, internal scoring systems designed to identify characteristics consistent with prompt injection have recorded a growing number of high-confidence matches. The upward trend suggests that attackers are actively experimenting with these techniques.

Recent examples of prompt injection attacks

Two early examples of this evolving threat are HashJack and ShadowLeak, which illustrate prompt injection in practice.

HashJack is a novel prompt injection technique discovered in November 2025 that exploits AI-powered web browsers and agentic AI browser assistants. By hiding malicious instructions within the URL fragment (after the # symbol) of a legitimate, trusted website, attackers can trick AI web assistants into performing malicious actions – potentially inserting phishing links, fake contact details, or misleading guidance directly into what appears to be a trusted AI-generated output.

ShadowLeak is a prompt injection method to exfiltrate PII identified in September 2025. This was a flaw in ChatGPT (now patched by OpenAI) which worked via an agent connected to email. If attackers sent the target an email containing a hidden prompt, the agent was tricked into leaking sensitive information to the attacker with no user action or visible UI.

What’s the risk of email-delivered prompt injection attacks?

Enterprise AI assistants often have complete visibility across emails, documents, and internal platforms. This means an attacker does not need to compromise credentials or move laterally through an environment. If successful, they can influence the AI to retrieve relevant information seamlessly, without the labor of compromise and privilege escalation.

The first risk is data exfiltration. In a prompt injection scenario, malicious instructions may be embedded within an ordinary email. As in the ShadowLeak attack, when AI processes that content as part of a legitimate task, it may interpret the hidden text as an instruction. This could result in the AI disclosing sensitive data, summarizing confidential communications, or exposing internal context that would otherwise require significant effort to obtain.

The second risk is agentic workflow poisoning. As AI systems take on more active roles, prompt injection can influence how they behave over time. An attacker could embed instructions that persist across interactions, such as causing the AI to include malicious links in responses or redirect users to untrusted resources. In this way, the attacker inserts themselves into the workflow, effectively acting as a man-in-the-middle within the AI system.

Why can’t other solutions catch email-delivered prompt injection attacks?

AI prompt injection challenges many of the assumptions that traditional email security is built on. It does not fit the usual patterns of phishing, where the goal is to trick a user into clicking a link or opening an attachment.  

Most security solutions are designed to detect signals associated with user engagement: suspicious links, unusual attachments, or social engineering cues. Prompt injection avoids these indicators entirely, meaning there are fewer obvious red flags.

In this case, the intention is actually the opposite of user solicitation. The objective is simply for the email to be delivered and remain in the inbox, appearing benign and unremarkable. The malicious element is not something the recipient is expected to engage with, or even notice.

Detection is further complicated by the nature of the prompts themselves. Unlike known malware signatures or consistent phishing patterns, injected prompts can vary widely in structure and wording. This makes simple pattern-matching approaches, such as regex, unreliable. A broad rule set risks generating large numbers of false positives, while a narrow one is unlikely to capture the diversity of possible injections.

How does Darktrace catch these types of attacks?

The Darktrace approach to email security more generally is to look beyond individual indicators and assess context, which also applies here.  

For example, our prompt density score identifies clusters of prompt-like language within an email rather than just single occurrences. Instead of treating the presence of a phrase as a blocking signal, the focus is on whether there is an unusual concentration of these patterns in a way that suggests injection. Additional weighting can be applied where there are signs of obfuscation. For example, text that is hidden from the user – such as white font or font size zero – but still readable by AI systems can indicate an attempt to conceal malicious prompts.

This is combined with broader behavioral signals. The same communication context used to detect other threats remains relevant, such as whether the content is unusual for the recipient or deviates from normal patterns.

Ask your email provider about email-delivered AI prompt injection

Prompt injection targets not just employees, but the AI systems they rely on, so security approaches need to account for both.

Though there are clear indications of emerging activity, it remains to be seen how popular prompt injection will be with attackers going forward. Still, considering the potential impact of this attack type, it’s worth checking if this risk has been considered by your email security provider.

Questions to ask your email security provider

  • What safeguards are in place to prevent emails from influencing AI‑driven workflows over time?
  • How do you assess email content that’s benign for a human reader, but may carry hidden instructions intended for AI systems?
  • If an email contains no links, no attachments, and no social engineering cues, what signals would your platform use to identify malicious intent?

Visit the Darktrace / EMAIL product hub to discover how we detect and respond to advanced communication threats.  

Learn more about securing AI in your enterprise.

Continue reading
About the author
Kiri Addison
Senior Director of Product
Your data. Our AI.
Elevate your network security with Darktrace AI