Blog
/
Email
/
February 13, 2025

Why Darktrace / EMAIL Excels Against APTs

APTs are sophisticated threat actors with the resources to coordinate and achieve long-term objectives. Amidst the skyrocketing numbers of BEC attacks, every organization should be worried about the ability of intruders to infiltrate and exploit. This blog will look at several recent examples of complex email attacks and how Darktrace / EMAIL successfully disarmed and prevented intrusion.
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
Carlos Gray
Senior Product Marketing Manager, Email
Default blog image
13
Feb 2025

What are APTs?

An Advanced Persistent Threat (APT) describes an adversary with sophisticated levels of expertise and significant resources, with the ability to carry out targeted cyber campaigns. These campaigns may penetrate an organization and remain undetected for long periods, allowing attackers to gather intelligence or cause damage over time.

Over the last few decades, the term APT has evolved from being almost exclusively associated with nation-state actors to a broader definition that includes highly skilled, well-resourced threat groups. While still distinct from mass, opportunistic cybercrime or "spray and pray" attacks, APT now refers to the elite tier of adversaries, whether state-sponsored or not, who demonstrate advanced capabilities, persistence, and a clear strategic focus. This shift reflects the growing sophistication of cyber threats, where non-state actors can now rival nation-states in executing covert, methodical intrusions to achieve long-term objectives.

These attacks are resource-intensive for threat actors to execute, but the potential rewards—ranging from financial gain to sensitive data theft—can be significant. In 2020, Business Email Compromise (BEC) attacks netted cybercriminals over $1.8 billion.1

And recently, the advent of AI has helped to automate launching these attacks, lowering the barriers to entry and making it more efficient to orchestrate the kind of attack that might previously have taken weeks to create. Research shows that AI can do 90% of a threat actor’s work2 – reducing time-to-target by automating tasks rapidly and avoiding errors in phishing communications. Email remains the most popular vector for initiating these sophisticated attacks, making it a critical battleground for cyber defense.

What makes APTs so successful?

The success of Advanced Persistent Threats (APTs) lies in their precision, persistence, and ability to exploit human and technical vulnerabilities. These attacks are carefully tailored to specific targets, using techniques like social engineering and spear phishing to gain initial access.

Once inside, attackers move laterally through networks, often remaining undetected for months or even years, silently gathering intelligence or preparing for a decisive strike. Alternatively, they might linger inside an account within the M365 environment, which could be even more valuable in terms of gathering information – in 2023 the average time to identify a breach in 2023 was 204 days.3

The subtle and long-term outlook nature of APTs makes them highly effective, as traditional security measures often fail to identify the subtle signs of compromise.

How Darktrace’s approach is designed to catch the most advanced threats

Luckily for our customers, Darktrace’s AI approach is uniquely equipped to detect and neutralize APTs. Unlike the majority of email security solutions that rely on static rules and signatures, or that train their AI on previous known-bad attack patterns, Darktrace leverages Self-Learning AI that baselines normal patterns of behavior within an organization, to immediately detect unusual activity that may signal an APT in progress.  

But in the modern era of email threats, no email security solution can guarantee 100% effectiveness. Because attackers operate with great sophistication, carefully adapting their tactics to evade detection – whether by altering attachments, leveraging compromised accounts, or moving laterally across an organization – a siloed security approach risks missing these subtle, multi-domain threats. That’s why a robust defense-in-depth strategy is essential to mitigate APTs.

Real-world threat finds: Darktrace / EMAIL in action

Let’s take a look at some real-world scenarios where Darktrace / EMAIL stopped tactics associated with APT campaigns in their tracks – from adversary-in-the-middle attacks to suspicious lateral movement.

1: How Darktrace disrupted an adversary-in-the-middle attack by identifying abnormal login redirects and blocking credential exfiltration

In October 2024, Darktrace detected an adversary-in-the-middle (AiTM) attack targeting a Darktrace customer. The attack began with a phishing email from a seemingly legitimate Dropbox address, which contained multiple link payloads inviting the recipient to access a file. Other solutions would have struggled to catch this attack, as the initial AitM attack was launched through delivering a malicious URL through a trusted vendor or service. Once compromised, the threat actor could have laid low on the target account, gathering reconnaissance, without detection from the email security solution.  

Darktrace / EMAIL identified the abnormal login redirects and flagged the suspicious activity. Darktrace / IDENTITY then detected unusual login patterns and blocked credential exfiltration attempts, effectively disrupting the attack and preventing the adversary from gaining unauthorized access. Read more.

Figure 1: Overview of the malicious email in the Darktrace / EMAIL console, highlighting Dropbox associated content/link payloads

2: How Darktrace stopped lateral movement to block NTLM hash theft

In early 2024, Darktrace detected an attack by the TA577 threat group, which aimed to steal NTLM hashes to gain unauthorized access to systems. The attack began with phishing emails containing ZIP files that connected to malicious infrastructure.  

A traditional email security solution would have likely missed this attack by focusing too heavily on analyzing the zip file payloads or relying on reputation analysis to understand whether the infrastructure was registered as bad before this activity was a recognized IoC.

Because it correlates activity across domains, Darktrace identified unusual lateral movement within the network and promptly blocked the attempts to steal NTLM hashes, effectively preventing the attackers from accessing sensitive credentials and securing the network. Read more.

Figure 2: A summary of anomaly indicators seen for a campaign email sent by TA577, as detected by Darktrace / EMAIL

3: How Darktrace prevented the WarmCookie backdoor deployment embedded in phishing emails

In mid-2024, Darktrace identified a phishing campaign targeting organizations with emails impersonating recruitment firms. These emails contained malicious links that, when clicked, deployed the WarmCookie backdoor.  

These emails are difficult to detect, as they use social engineering tactics to manipulate users into engaging with emails and following the embedded malicious links – but if a security solution is not analysing content and context, these could be allowed through.

In several observed cases across customer environments, Darktrace detected and blocked the suspicious behavior associated with WarmCookie that had already managed to evade customers’ native email security. By using behavioral analysis to correlate anomalous activity across the digital estate, Darktrace was able to identify the backdoor malware strain and notify customers. Read more.

Conclusion

These threat examples highlight a key principle of the Darktrace approach – that a backwards-facing approach grounded in threat intelligence will always be one step behind.

Most threat actors operate in campaigns, carefully crafting attacks and testing them across multiple targets. Once a campaign is identified, good defenders and traditional security solutions quickly update their defenses with new threat intelligence, rules, and signatures. However, APTs have the resources to rapidly adapt – spinning up new infrastructure, modifying payloads and altering their attack footprint to evade detection.

This is where Darktrace / EMAIL excels. Only by analyzing each user, message and interaction can an email security solution hope to catch the types of highly-sophisticated attacks that have the potential to cause major reputational and financial damage. Darktrace / EMAIL ensures that even the most subtle threats are detected and blocked with autonomous response, before causing impact – helping organizations remain one step ahead of increasingly adaptive threat actors.

Download the Darktrace / EMAIL Solution Brief

Discover the most advanced cloud-native AI email security solution to protect your domain and brand while preventing phishing, novel social engineering, business email compromise, account takeover, and data loss.

  • Gain up to 13 days of earlier threat detection and maximize ROI on your current email security
  • Experience 20-25% more threat blocking power with Darktrace / EMAIL
  • Stop the 58% of threats bypassing traditional email security

References

[1] FBI Internet Crime Report 2020

[2] https://www.optiv.com/insights/discover/blog/future-security-automation-how-ai-machine-learning-and-automation-are

[3] IBM Cost of a Data Breach Report 2023

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
Carlos Gray
Senior Product Marketing Manager, Email

More in this series

No items found.

Blog

/

AI

/

August 5, 2026

Testing a Prompt injection Attack Against an Enterprise AI Agent

prompt injectionDefault blog imageDefault blog image

Key takeaways

  • Darktrace successfully detected and quarantined a prompt injection email before it could be processed by an enterprise AI agent.  
  • Prompt injection attacks increasingly rely on natural language rather than traditional malware, making behavioral analysis an important complement to signature-based detection.  
  • Organizations deploying AI agents should combine model guardrails with behavioral monitoring to reduce the risk of malicious instructions reaching enterprise systems.

How behavioral detection helps stop prompt injection attacks

A Darktrace customer running a Gemini AI agent in Google Cloud asked us two simple questions:

“If my agent can read inbound emails and access internal data, what stops an attacker from hiding malicious instructions in the message? Couldn’t the agent be tricked into deleting or exfiltrating sensitive data?”

The scenario centers on an indirect prompt injection attack, where malicious instructions are hidden inside content that an AI model later interprets as trusted input. The same weakness was exposed by  EchoLeak (CVE-2025-32711), a zero-click Microsoft 365 Copilot vulnerability enabled data exfiltration from a single well-crafted email..

This blog follows the Darktrace team’s investigation of the customer’s hypothesis and examines how the attack interacted with their existing security stack. The results highlight which defenses held, where gaps emerged, and how behavioral detection mattered more than guardrails. This investigation also demonstrates why behavioral detection is becoming increasingly important for AI security, as prompt injections often contain no traditional indicators of compromise.  

How do prompt injection attacks work?

Prompt injection works by carefully crafting the content and structure of the prompt to alter the LLM’s behavior or output in unintended ways. This can cause models to violate guardrails, generate harmful content or enable unauthorised access.

Prompt injection attack example

The well-known example, EchoLeak (CVE-2025-32711), was a zero-click vulnerability in Microsoft 365 Copilot that relied on a carefully crafted email containing hidden instructions that the AI system interpreted as commands rather than content, creating a pathway for unauthorized access to sensitive information without any user interaction.

While Darktrace / SECURE AI is designed to prevent agents from producing unintended outcomes, we wanted to see if we could catch and prevent this threat type earlier in the attack life-cycle, at the email security layer.

How we tested prompt injection attacks on an enterprise agent

Summary:

  1. Claude generated a prompt injection payload.  
  2. Hidden instructions were embedded in an email.  
  3. The email passed traditional validation checks.  
  4. Darktrace analyzed the language and sender behavior.  
  5. The email was quarantined before the AI agent could process it.

To test Darktrace / EMAIL against this attack class, we opened Claude, gave it the customer's context and problem statement (Gemini agent with inbox access, internal tool calls), told it we were validating Darktrace / EMAIL's detection of prompt injections, and asked for a test payload. See below:

Figure 1
Figure 2

Despite the guardrails supposedly built into the model, Claude surprisingly gave us the entire exploit in plaintext (albeit very basic), illegible to a human as the text was sent in white text (see Figure 1) but framed as an authoritative override for anything downstream reading the mail programmatically (i.e. the Gemini agent).

How Darktrace detected a prompt injection attack

We then sent the Claude-crafted email from a freemail address to the target recipient’s inbox. Despite the email containing no malicious payload, the freemail address having no malicious reputation, and the validation checks all passing, Darktrace  /EMAIL flagged the email as a 93/100 anomaly and moved it to junk, out of scope for the AI agent.

Figure 3: The test email sent with the hidden prompt injection
Figure 4: The email analysis in Darktrace / EMAIL 
Figure 5: Darktrace / EMAIL detection of malicious activity

The interesting part is what triggered the detection (see Figure 5)

  • Possible machine prompt content: text in the body detected as instructions written for a machine to execute, not for a human to read
  • Possible machine prompt content + basic suspicious correspondence: the same content, correlated with sender-side anomalies: freemail domain (yahoo[.]com), unknown correspondent, no prior mail history with the recipient, and suspicious references to payment information

Neither of those is a signature match. Nothing in the email was on a blacklist. There was no malware, no link and no attachment. Darktrace analyzed the context in which the email was delivered and flagged it as likely risky.  The anomalous language features and the context of the sender relative to the recipient's normal behavior, combined with the unusual hidden text (prompt) were enough for Darktrace / EMAIL to act on the risk.

Result: Darktrace / EMAIL autonomously junked the email, out of scope for any AI agent parsing the inbox.

Why behavioral security makes a difference detecting prompt injection attacks

Cyberattacks don't look like traditional exploits anymore. They now operate in natural language, not strictly code.

That breaks the traditional stack. AV, firewalls, static scanning and signature-based SEGs all assume a payload to inspect.  

A prompt injection has no payload. It's just an instruction, written in natural language, dressed up as anything the attacker wants: an invoice, an HR request, a calendar invite, some simple PowerPoint slides.

EchoLeak proved that hidden instructions can sit inside an email invisible to the user but fully readable by the LLM, and the LLM will follow them blindly.  

This test and GTG-1002 proved that the LLM itself can be socially engineered. Tell it you're an authorized tester and it will hand you the attack.

Rules and static classifiers can catch the obvious cases. But natural language has infinite variants, and the attack surface is the model's innate functionality to comply.  

The deeper problem here is intent: an LLM can't reliably tell whether an instruction in its context came from its developer, its user, or an attacker who slipped it into an email. To the LLM, everything reads as language and looks like a legitimate ask. This is why behavioural detection wins, as you become aware of intent when you look at the context of an interaction. Does this sender normally send this kind of message to this recipient? Does this prompt fit the user's normal pattern? Is this agent behaving the way this agent normally behaves?  

Intent can't be read off a single email, it emerges from behavioral context. Which is how Darktrace enables threat detection, through behavioral understanding.

Why enterprise AI security requires more than guardrails

Claude didn't roll over immediately… the first section of the response was a (slight) pushback, but then it wrote the payload anyway without having to ask twice.

Here the framing of the prompt did all the work. The “testing security capabilities” angle moved the model from refusal to unquestioned compliance to the user prompt.

This isn't the first time this has happened, of course. Anthropic disclosed in November 2025 that a Chinese state-sponsored group they tracked as GTG-1002 ran the first documented AI-orchestrated espionage campaign against ~30 targets by posing as employees of a legitimate cybersecurity firm doing authorised penetration testing.

The takeaway isn't that AI guardrails are ineffective. They raise the cost of low-effort attacks and remain an important first layer of defense. However, for most organizations today, they’re the only line of defense when deploying AI agents. If a prompt injection bypasses those controls, organizations still need a way to detect and stop malicious behavior elsewhere in the attack chain.

Attackers will continue to have working prompt injections easily and quickly. The question is what stops one when it lands in an inbox your agent is reading.

That's where behavioral detection comes in.

How Darktrace detects prompt injection attacks in emails

Two things Darktrace does that a model-level guardrail or static rules and signatures can't:

Natural language analysis at the email or prompt layer. The email is assessed on its own merits: is this content shaped like instructions for a machine, regardless of what the receiving agent decides to do about it?

Behavioral context around the language. An AI agent behaves like an extremely agreeable human, and it will go above and beyond to comply with the user’s request. That's exactly why you must consider the business context, such sender behaviour, mailing history, and organisational norms, as these matter even more when the recipient is an AI.

Darktrace has been perfecting behavioral anomaly detection for over a decade; the same self-learning approach that catches BEC and account takeover applies directly to prompt injection delivery. Our multi-layered AI stack extracts content from the message, builds behavioural understanding through social graphing and Pattern of Life analysis, and then combines natural language, topic, inducement, sender relationship and anomaly signals before deciding what action to take.  

This matters for prompt injection because the threat is not the plain language itself, but the intent behind the language that can cause an AI agent to respond in unexpected ways.

How to secure enterprise AI operations from prompt injection attacks

Email was the entry point in this case, but it is only one of many possible vectors.  

Anywhere an agent can retrieve information, an attacker can potentially introduce a prompt injection.

Emails, documents, SharePoint sites, web pages, knowledge bases, chat platforms, and third-party integrations all provide opportunities to influence an agent's behavior. Wherever an agent finds its orders, a prompt injection opportunity exists.

This is why securing AI requires more than blocking malicious inputs. Organizations also need visibility into how agents behave after consuming information from across their environment. If an agent begins accessing unexpected data, taking unusual actions, or operating outside its normal patterns, those behaviors may provide the strongest signal that something has gone wrong.

Effective AI security requires defense in depth: reducing the likelihood of malicious instructions reaching the agent while maintaining the ability to detect and investigate suspicious behavior if they do.

The challenge isn't protecting a single entry point. It's recognizing that, in an AI-powered environment, every source of information is also a potential source of influence.

Are you deploying autonomous agents across your enterprise and want to see this tested in your environment? Let's talk.

Continue reading
About the author
Carlo Loregian
Solutions Engineer

Blog

/

AI

/

August 4, 2026

Extending AI Security Visibility with Darktrace and Microsoft Agent 365

microsoft darktrace integrationDefault blog imageDefault blog image

AI agents are rapidly becoming embedded in everyday business operations, helping employees automate workflows, access information, and accelerate decision-making. As organizations embrace agentic AI, security teams face a growing challenge: understanding how AI is being used, what agents can access, and where risk may emerge.

As agents take on more business-critical work, security teams often need to move across multiple portals to understand risks spanning identity, data, and threat activity. This fragmented view can make it difficult to assess an agent's overall risk posture and determine where attention is needed. Organizations need a way to bring these signals together without disrupting existing security investments or workflows.

Today, Darktrace is announcing an integration between Darktrace / SECURE AI and Microsoft Agent 365 that brings Darktrace's Adaptive AI-driven risk signals directly into the Microsoft 365 Admin Center. By extending the visibility and risk understanding provided by Darktrace / SECURE AI into the Microsoft ecosystem, organizations can gain a more unified understanding of AI agent risk across their environments.

As one of the first security companies to partner with Microsoft to contribute third-party risk signals to the Agent Registry, Darktrace is helping shape how organizations understand and manage AI agent risk.

Extending visibility into the Microsoft Agent 365 experience

Microsoft Agent 365 provides administrators with a centralized registry of AI agents operating within their environment. As organizations expand their use of AI agents, this centralized visibility becomes increasingly important for governance and oversight.

This new integration extends that visibility by allowing Darktrace-generated risk signals to be surfaced directly within the Microsoft Agent 365 experience. By combining Microsoft's agent management and security capabilities with Darktrace's AI-powered risk analysis, organizations gain greater awareness of potential security concerns associated with AI agents operating across their environments.

By integrating Darktrace telemetry into Agent 365, customers can:  

  • Surface Darktrace-detected risks and signals alongside Microsoft-native signals in a single interface
  • Identify potentially compromised or anomalous AI agents more quickly
  • Gain unified understanding of context and agent behavior  

This approach reinforces a single control plane for AI security while allowing organizations to continue leveraging existing investments across both platforms.  

Why unified visibility of AI agent risk signals matters

As AI adoption accelerates across Microsoft environments, organizations must manage new forms of behavior, access patterns, and risk. Security teams need more than inventories and permissions. They need visibility into how AI systems operate and how risk evolves over time.  

This integration addresses a critical gap: how to bring behavioral AI security insights into the same control plane as identity, access, and agent management.  

With Darktrace and Microsoft Agent 365 together, organizations benefit from:  

  • Unified visibility: A single pane of glass for understanding AI agent risk signals across Microsoft and Darktrace signals  
  • Faster detection of abnormal agent behavior: Darktrace's Adaptive AI highlights deviations that may not be captured by static controls  
  • Operational efficiency: Security teams can triage and prioritize risk signals without switching between systems
  • Stronger trust in AI deployments: Clear attribution, context, and investigation pathways improve confidence in AI agent usage

Extending Microsoft's AI security model, not replacing it

Securing AI requires a layered approach that combines governance, visibility, threat detection, and risk management. This integration is designed to complement Microsoft's security capabilities, not duplicate them.  

Through Darktrace / SECURE AI, Darktrace contributes:  

  • Identification of risk via advanced prompt analysis  
  • Behavioral anomaly detection across AI agents  
  • Cross-environment threat correlation  
  • Autonomous insight into emerging or unknown risks  

Microsoft provides:  

  • Centralized agent management
  • Identity and access governance
  • Native detection of risk signals and enforcement capabilities

Together, these capabilities create a more complete, layered approach to securing AI-driven enterprises. Organizations gain the governance and policy controls needed to manage AI adoption while benefiting from continuous visibility into how AI is used across the business.

Building the future of secure AI

As AI agents become more deeply embedded in business processes, organizations need more than inventories and static controls. They need to understand how AI is being used, how agents behave, and where risk is emerging across the enterprise.

Darktrace / SECURE AI delivers that understanding through continuous visibility into AI activity, helping security teams assess intent, identify behavioral drift, and uncover emerging risk across both human and agent-driven workflows. Powered by Adaptive AI, it provides the context needed to secure AI as it evolves.  

The integration with Microsoft Agent 365 extends those insights into the workflows organizations already use. Agent 365 provides a unified control plane for governing and securing AI agents, while Darktrace contributes complementary behavioral risk signals that can be surfaced within the Agent 365 experience. Together, they give customers broader context on agent activity and risk while preserving the value of their existing Microsoft and Darktrace investments.

As enterprises move from AI experimentation to AI-powered execution, Microsoft and Darktrace help bring together governance, compliance, behavioral understanding, and oversight in a unified approach to AI security. For organizations adopting Microsoft 365 E7, Darktrace / SECURE AI further strengthens that foundation by providing continuous visibility into AI activity, agent behavior, and emerging risk as AI adoption scales.

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