Blog
/
Compliance
/
July 17, 2024

What you need to know about the new SEC Cybersecurity rules

In July 2023, the U.S. Securities and Exchange Commission (SEC) adopted new rules concerning cybersecurity incidents and disclosures. This blog describes the new rules and demonstrates how Darktrace can help organizations achieve compliance with these standards.
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
Kendra Gonzalez Duran
Principal Analyst
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
17
Jul 2024

What is new in 2023 to SEC cybersecurity rules?

Form 8-K Item 1.05: Requiring the timely disclosure of material cybersecurity incidents.

Regulation S-K item 106: requiring registrants’ annual reports on Form 10-K to address cybersecurity risk management, strategy, and governance processes.

Comparable disclosures are required for reporting foreign private issuers on Forms 6-K and 20-F respectively.

What is Form 8-K Item 1.05 SEC cybersecurity rules?

Form 8-K Item 1.05 requires the following to be reported within four business days from when an incident is determined to be “material” (1), unless extensions are granted by the SEC under certain qualifying conditions:

“If the registrant experiences a cybersecurity incident that is determined by the registrant to be material, describe the material aspects of the nature, scope, and timing of the incident, and the material impact or reasonably likely material impact on the registrant, including its financial condition and results of operations.” (2, 3)

How does the SEC define cybersecurity incident?

Cybersecurity incident defined by the SEC means an unauthorized occurrence, or a series of related unauthorized occurrences, on or conducted through a registrant’s information systems that jeopardizes the confidentiality, integrity, or availability of a registrant’s information systems or any information residing therein. (4)

How can Darktrace assist in the process of disclosing incidents to the SEC?

Accelerate reporting

Darktrace’s Cyber AI Analyst generates automated reports that synthesize discrete data points potentially indicative of cybersecurity threats, forming reports that provide an overview of the evolution and impact of a threat.

Thus, when a potential threat is identified by Darktrace, AI Analyst can quickly compile information that organizations might include in their disclosure of an occurrence they determined to be material, including the following: incident timelines, incident events, incident summary, related model breaches, investigation process (i.e., how Darktrace’s AI conducted the investigation), linked incident events, and incident details. The figure below illustrates how Darktrace compiles and presents incident information and insights in the UI.

Overview of information provided in an ‘AI Analyst Report’ that could be relevant to registrants reporting a material cybersecurity incident to the SEC
Figure 1: Overview of information provided in an ‘AI Analyst Report’ that could be relevant to registrants reporting a material cybersecurity incident to the SEC

It should be noted that Instruction 4 to the new Form 8-K Item 1.05 specifies the “registrant need not disclose specific or technical information about its planned response to the incident or its cybersecurity systems, related networks and devices, or potential system vulnerabilities in such detail as would impede the registrant’s response or remediation of the incident” (5).

As such, the incident report generated by Darktrace may provide more information, including technical details, than is needed for the 8-K disclosure. In general, users should take appropriate measures to ensure that the information they provide in SEC reports meets the requirements outlined by the relevant regulations. Darktrace cannot recommend that an incident should be reported, nor report an incident itself.

Determine if a cybersecurity incident is material

Item 1.05 requires registrants to determine for themselves whether cybersecurity incidents qualify as ‘material’. This involves considerations such as ‘the nature scope and timing of the incident, and the material impact or reasonably likely material impact on the registrant, including its financial condition and results of operations.’

While it is up to the registrant to determine, consistent with existing legal standards, the materiality of an incident, Darktrace’s solution can provide relevant information which might aid in this evaluation. Darktrace’s Threat Visualizer user interface provides a 3-D visualization of an organization’s digital environment, allowing users to assess the likely degree to which an attack may have spread throughout their digital environment. Darktrace Cyber AI Analyst identifies connections among discrete occurrences of threatening activity, which can help registrants quickly assess the ‘scope and timing of an incident'.

Furthermore, in order to establish materiality it would be useful to understand how an attack might extend across recipients and environments. In the image below, Darktrace/Email identifies how a user was impacted across different platforms. In this example, Darktrace/Email identified an attacker that deployed a dual channel social engineering attack via both email and a SaaS platform in an effort to acquire login credentials. In this case, the attacker useding a legitimate SharePoint link that only reveals itself to be malicious upon click. Once the attacker gained the credentials, it proceeded to change email rules to obfuscate its activity.

Darktrace/Email presents this information in one location, making such investigations easier for the end user.

Darktrace/Email indicating a threat across SaaS and email
Figure 2: Darktrace/Email indicating a threat across SaaS and email

What is regulation S-K item 106 of the SEC cybersecurity rules?

The new rules add Item 106 to Regulation S-K requiring registrants to disclose certain information regarding their risk management, strategy, and governance relating to cybersecurity in their annual reports on Form 10-K. The new rules add Item 16K to Form 20-F to require comparable disclosure by [foreign private issuers] in their annual reports on Form 20-F. (6)

SEC cybersecurity rules: Risk management

Specifically, with respect to risk management, Item 106(b) and Item 16K(b) require registrants to describe their processes, if any, for assessing, identifying, and managing material risks from cybersecurity threats, as well as whether any risks from cybersecurity threats, including as a result of any previous cybersecurity incidents, have materially affected or are reasonably likely to materially affect them. The new rules include a non-exclusive list of disclosure items registrants should provide based on their facts and circumstances. (6)

SEC cybersecurity rules: Governance

With respect to governance, Item 106 and Item 16K require registrants to describe the board of directors’ oversight of risks from cybersecurity threats (including identifying any board committee or subcommittee responsible for such oversight) and management’s role in assessing and managing material risks from cybersecurity threats. (6)

How can Darktrace solutions aid in disclosing their risk management, strategy, and governance related to cybersecurity?

Impact scores

Darktrace End-to-End (E2E) leverages AI to understand the complex relationships across users and devices to model possible attack paths, giving security teams a contextual understanding of risk across their digital environments beyond isolated CVEs or CVSS scores. Additionally, teams can prioritize risk management actions to increase their cyber resilience through the E2E Advisory dashboard.

Attack paths consider:

  • Potential damages: Both the potential consequences if a given device was compromised and its immediate implications on other devices.
  • Exposure: Devices' level of interactivity and accessibility. For example, how many emails does a user get via mailing lists and from what kind of sources?
  • Impact: Where a user or asset sits in terms of the IT or business hierarchy and how they communicate with each other. Darktrace can simulate a range of possible outcomes for an uncertain event.
  • Weakness: A device’s patch latency and difficulty, a composite metric that looks at attacker MITRE methods and our own scores to determine how hard each stage of compromise is to achieve.

Because the SEC cybersecurity rules require “oversight of risks from cybersecurity threats” and “management’s role in assessing and managing material risks from cybersecurity threats” (6), the scores generated by Darktrace E2E can aid end-user’s ability to identify risks facing their organization and assign responsibilities to address those risks.

E2E attack paths leverage a deep understanding of a customer’ digital environment and highlight potential attack routes that an attacker could leverage to reach critical assets or entities. Difficulty scores (see Figure 5) allow security teams to measure potential damage, exposure, and impact of an attack on a specific asset or entity.

An example of an attack path in a digital environment
Figure 3: An example of an attack path in a digital environment

Automatic executive threat reports

Darktrace’s solution automatically produces Executive Threat Reports that present a simple visual overview of model breaches (i.e., indicators of unusual and threatening behaviors) and activity in the network environment. Reports can be customized to include extra details or restricted to high level information.

These reports can be generated on a weekly, quarterly, and yearly basis, and can be documented by registrants in relation to Item 106(b) to document parts of their efforts toward assessing, identifying, and managing material risks from cybersecurity threats.

Moreover, Cyber AI Analyst incident reports (described above) can be leveraged to document key details concerning significant previous incidents identified by the Darktrace solution that the registrant determined to be ‘material’.

While the disclosures required by Item 106(c) relate to the governance processes by which the board of directors, the management, and other responsible bodies within an organization oversee risks resulting from cybersecurity threats, the information provided by Darktrace’s Executive Threat Reports and Cyber AI Analyst incident reports can also help relevant stakeholders communicate more effectively regarding the threat landscape and previous incidents.

DISCLAIMER

The material above is provided for informational purposes only. This summary does not constitute legal or compliance advice, recommendations, or guidance. Darktrace encourages you to verify the contents of this summary with your own advisors.

References

  1. Note that the rule does not set forth any specific timeline between the incident and the materiality determination, but the materiality determination should be made without unreasonable delay.
  2. https://www.sec.gov/files/form8-k.pdf
  3. https://www.sec.gov/news/press-release/2023-139
  4. https://www.ecfr.gov/current/title-17/chapter-II/part-229
  5. https://www.sec.gov/files/form8-k.pdf
  6. https://www.sec.gov/corpfin/secg-cybersecurity
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
Kendra Gonzalez Duran
Principal 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