Blog
/
Network
/
February 15, 2024

Detecting & Containing Gootloader Malware

Learn how Darktrace helps detect and contain multi-functional threats like the Gootloader malware. Stay ahead of cyber threats with Darktrace AI solutions.
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
Ashiq Shafee
Cyber Security Analyst
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
15
Feb 2024

What is multi-functional malware?

While traditional malware variants were designed with one specific objective in mind, the emergence of multi-functional malware, such as loader malware, means that organizations are likely to be confronted with multiple malicious tools and strains of malware at once. These threats often have non-linear attack patterns and kill chains that can quickly adapt and progress quicker than human security teams are able to react. Therefore, it is more important than ever for organizations to adopt an anomaly approach to combat increasingly versatile and fast-moving threats.

Example of Multi-functional malware

One example of a multi-functional malware recently observed by Darktrace can be seen in Gootloader, a multi-payload loader variant that has been observed in the wild since 2020. It is known to primarily target Windows-based systems across multiple industries in the US, Canada, France, Germany, and South Korea [1].  

How does Gootloader malware work?

Once installed on a target network, Gootloader can download additional malicious payloads that allow threat actors to carry out a range of harmful activities, such as stealing sensitive information or encrypting files for ransom.

The Gootloader malware is known to infect networks via search engine optimization (SEO) poisoning, directing users searching for legitimate documents to compromised websites hosting a malicious payload masquerading as the desired file.

If the malware remains undetected, it paves the way for a second stage payload known as Gootkit, which functions as a banking trojan and information-stealer, or other malware tools including Cobalt Strike and Osiris [2].

Darktrace detection of Gootloader malware

In late 2023, Darktrace observed one instance of Gootloader affecting a customer in the US. Thanks to its anomaly-focused approach, Darktrace quickly identified the anomalous activity surrounding this emerging attack and brought it to the immediate attention of the customer’s security team. All the while, Darktrace's Autonomous Response was in place and able to autonomously intervene, containing the suspicious activity and ensuring the Gootloader compromise could not progress any further.

Autonomous Response was in place and able to autonomously intervene, containing the suspicious activity and ensuring the Gootloader compromise could not progress any further.

In September 2023, Darktrace identified an instance of the Gootloader malware attempting to propagate within the network of a customer in the US. Darktrace identified the first indications of the compromise when it detected a device beaconing to an unusual external location and performing network scanning. Following this, the device was observed making additional command-and-control (C2) connections, before finally downloading an executable (.exe) file which likely represented the download of a further malicious payload.

As this customer had subscribed to the Proactive Notification Service (PTN), the suspicious activity was escalated to the Darktrace Security Operations Center (SOC) for further investigation by Darktrace’s expert analysts. The SOC team were able to promptly triage the incident and advise urgent follow-up actions.

Gootloader Attack Overview

Figure 1: Timeline of Anomalous Activities seen on the breach device.

Initial Beaconing and Scanning Activity

On September 21, 2023, Darktrace observed the first indications of compromise on the network when a device began to make regular connections to an external endpoint that was considered extremely rare for the network, namely ‘analyzetest[.]ir’.

Although the endpoint did not overtly seem malicious in nature (it appeared to be related to laboratory testing), Darktrace recognized that it had never previously been seen on the customer’s network and therefore should be treated with caution.  This initial beaconing activity was just the beginning of the malicious C2 communications, with several additional instances of beaconing detected to numerous suspicious endpoints, including funadhoo.gov[.]mv, tdgroup[.]ru’ and ‘army.mil[.]ng.

Figure 2: Initial beaconing activity detected on the breach device.

Soon thereafter, Darktrace detected the device performing internal reconnaissance, with an unusually large number of connections to other internal locations observed. This scanning activity appeared to primarily be targeting the SMB protocol by scanning port 445.

Within seconds of Darktrace's detection of this suspicious SMB scanning activity, Darktrace's Autonomous Response moved to contain the compromise by blocking the device from connecting to port 445 and enforcing its ‘pattern of life’. Darktrace’s Self-Learning AI enables it to learn a device’s normal behavior and recognize if it deviates from this; by enforcing a pattern of life on an affected device, malicious activity is inhibited but the device is allowed to continue its expected activity, minimizing disruption to business operations.

Figure 3: The breach device Model Breach Event Log showing Darktrace identifying suspicious SMB scanning activity and the corresponding respose actions.

Following the initial detection of this anomalous activity, Darktrace’s Cyber AI Analyst launched an autonomous investigation into the beaconing and scanning activity and was able to connect these seemingly separate events into one incident. AI Analyst analyzes thousands of connections to hundreds of different endpoints at machine speed and then summarizes its findings in a single pane of glass, giving customers the necessary information to assess the threat and begin remediation if necessary. This significantly lessens the burden for human security teams, saving them previous time and resources, while ensuring they maintain full visibility over any suspicious activity on their network.

Figure 4: Cyber AI Analyst incident log summarizing the technical details of the device’s beaconing and scanning behavior.

Beaconing Continues

Darktrace continued to observe the device carrying out beaconing activity over the next few days, likely representing threat actors attempting to establish communication with their malicious infrastructure and setting up a foothold within the customer’s environment. In one such example, the device was seen connecting to the suspicious endpoint ‘fysiotherapie-panken[.]nl’. Multiple open-source intelligence (OSINT) vendors reported this endpoint to be a known malware delivery host [3].

Once again, Darktrace Autonomous Response was in place to quickly intervene in response to these suspicious external connection attempts. Over the course of several days, Darktrace blocked the offending device from connecting to suspicious endpoints via port 443 and enforced its pattern of life. These autonomous actions by Darktrace effectively mitigated and contained the attack, preventing it from escalating further along the kill chain and providing the customer’s security team crucial time to take act and employ their own remediation.

Figure 5: A sample of the Autonomous Response actions that was applied on the affected device.

Possible Payload Retrieval

A few days later, on September 26, 2023, Darktrace observed the affected device attempting to download a Windows Portable Executable via file transfer protocol (FTP) from the external location ‘ftp2[.]sim-networks[.]com’, which had never previously been seen on the network. This download likely represented the next step in the Gootloader infection, wherein additional malicious tooling is downloaded to further cement the malicious actors’ control over the device. In response, Darktrace immediately blocked the device from making any external connections, ensuring it could not download any suspicious files that may have rapidly escalated the attackers’ efforts.

Figure 6: DETECT’s identification of the offending device downloading a suspicious executable file via FTP.

The observed combination of beaconing activity and a suspicious file download triggered an Enhanced Monitoring breach, a high-fidelity DETECT model designed to detect activities that are more likely to be indicative of compromise. These models are monitored by the Darktrace SOC round the clock and investigated by Darktrace’s expert team of analysts as soon as suspicious activity emerges.

In this case, Darktrace’s SOC triaged the emerging activity and sent an additional notice directly to the customer’s security team, informing them of the compromise and advising on next steps. As this customer had subscribed to Darktrace’s Ask the Expert (ATE) service, they also had a team of expert analysts available to them at any time to aid their investigations.

Figure 7: Enhanced Monitoring Model investigated by the Darktrace SOC.

Conclusion

Loader malware variants such as Gootloader often lay the groundwork for further, potentially more severe threats to be deployed within compromised networks. As such, it is crucial for organizations and their security teams to identify these threats as soon as they emerge and ensure they are effectively contained before additional payloads, like information-stealing malware or ransomware, can be downloaded.

In this instance, Darktrace demonstrated its value when faced with a multi-payload threat by detecting Gootloader at the earliest stage and responding to it with swift targeted actions, halting any suspicious connections and preventing the download of any additional malicious tooling.

Darktrace DETECT recognized that the beaconing and scanning activity performed by the affected device represented a deviation from its expected behavior and was indicative of a potential network compromise. Meanwhile, Darktrace ensured that any suspicious activity was promptly shut down, buying crucial time for the customer’s security team to work with Darktrace’s SOC to investigate the threat and quarantine the compromised device.

Credit to: Ashiq Shafee, Cyber Security Analyst, Qing Hong Kwa, Senior Cyber Analyst and Deputy Analyst Team Lead, Singapore

Appendices

Darktrace DETECT Model Detections

Anomalous Connection / Rare External SSL Self-Signed

Device / Suspicious SMB Scanning Activity

Anomalous Connection / Young or Invalid Certificate SSL Connections to Rare

Compromise / High Volume of Connections with Beacon Score

Compromise / Beacon to Young Endpoint

Compromise / Beaconing Activity To External Rare

Compromise / Slow Beaconing Activity To External Rare

Compromise / Beacon for 4 Days

Anomalous Connection / Suspicious Expired SSL

Anomalous Connection / Multiple Failed Connections to Rare Endpoint

Compromise / Sustained SSL or HTTP Increase

Compromise / Large Number of Suspicious Successful Connections

Compromise / Large Number of Suspicious Failed Connections

Device / Large Number of Model Breaches

Anomalous File / FTP Executable from Rare External Location

Device / Initial Breach Chain Compromise

RESPOND Models

Antigena / Network / Significant Anomaly / Antigena Breaches Over Time Block

Antigena / Network / Significant Anomaly / Antigena Significant Anomaly from Client Block

Antigena / Network/Insider Threat/Antigena Network Scan Block

Antigena / Network / Significant Anomaly / Antigena Enhanced Monitoring from Client Block

Antigena / Network / External Threat / Antigena Suspicious File Block

Antigena / Network / External Threat / Antigena File then New Outbound Block

Antigena / Network / External Threat / Antigena Suspicious Activity Block

List of Indicators of Compromise (IoCs)

Type

Hostname

IoCs + Description

explorer[.]ee - C2 Endpoint

fysiotherapie-panken[.]nl- C2 Endpoint

devcxp2019.theclearingexperience[.]com- C2 Endpoint

campsite.bplaced[.]net- C2 Endpoint

coup2pompes[.]fr- C2 Endpoint

analyzetest[.]ir- Possible C2 Endpoint

tdgroup[.]ru- C2 Endpoint

ciedespuys[.]com- C2 Endpoint

fi.sexydate[.]world- C2 Endpoint

funadhoo.gov[.]mv- C2 Endpoint

geying.qiwufeng[.]com- C2 Endpoint

goodcomix[.]fun- C2 Endpoint

ftp2[.]sim-networks[.]com- Possible Payload Download Host

MITRE ATT&CK Mapping

Tactic – Technique

Reconnaissance - Scanning IP blocks (T1595.001, T1595)

Command and Control - Web Protocols , Application Layer Protocol, One-Way Communication, External Proxy, Non-Application Layer Protocol, Non-Standard Port (T1071.001/T1071, T1071, T1102.003/T1102, T1090.002/T1090, T1095, T1571)

Collection – Man in the Browser (T1185)

Resource Development - Web Services, Malware (T1583.006/T1583, T1588.001/T1588)

Persistence - Browser Extensions (T1176)

References

1.     https://www.blackberry.com/us/en/solutions/endpoint-security/ransomware-protection/gootloader

2.     https://redcanary.com/threat-detection-report/threats/gootloader/

3.     https://www.virustotal.com/gui/domain/fysiotherapie-panken.nl

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
Ashiq Shafee
Cyber Security Analyst

More in this series

No items found.

Blog

/

Network

/

May 6, 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 6, 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