Blog
/
Email
/
April 18, 2023

Boosting Security Posture with Email Integration

Protect your organization from cyber-attacks with a strong security strategy. Learn how to safeguard against threats targeting email, cloud apps, and beyond.
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
Dan Fein
VP, Product
Written by
Carlos Gray
Senior Product Marketing Manager, Email
Default blog image
18
Apr 2023

On its own, Darktrace/Email™ stops attacks before they reach an employee’s inbox and considers both security teams and the employees themselves. But its value extends beyond email security, increased by its ability to integrate with the wider security ecosystem, including both Darktrace products and external tools. 

Darktrace’s understanding of you and your organization can be applied anywhere your company has data. This unifying approach to cyber security feeds AI outputs into each other, from threat prevention to detection and response, in order to harden the entire security posture autonomously and continuously. The AI also enriches other security solutions an organization has in place by both ingesting and sharing data. This degree of integration transforms a security stack so that it is greater than the sum of its parts. 

Integrating Beyond Email to Enhance Detection and Response 

Integrating email security with other areas of the digital estate bolsters defenses, while reducing required resources. With more data, security teams gain a better understanding of the security stack and how attacks move through the system.

Traditional security solutions do this by either manually aggregating inputs from various tools or using a SIEM without native integrations to collate data. In contrast, Darktrace’s integration provides real-time intelligence communications between products to inform security teams. 

For example, context of network activity can provide more holistic email security. There’s a strong correlation between the websites users visit and the people that they email, which means information like web traffic provides insight into email threats, and vice versa. 

If an organization receives an email from a strange new sender, that happens to be have been sent from a domain nobody has ever visited, that added context could influence the aggression levels of actions taken. Integrations with endpoint security extends this type of informed decision-making to remote environments. These examples highlight the patented power of Darktrace/Network™ and Darktrace/Endpoint™ when paired with email coverage. 

Diagram depicting the flow of email activity generated by Darktrace Email Security tool.
Figure 2. Darktrace/Email works with Darktrace/Network and Darktrace/Endpoint to generate email insights from web traffic and vice versa. 

Email activity is tied to cloud/SaaS application account activity in an even more direct way. In the case of an account takeover, a suspicious Microsoft 365 login becomes even more suspicious if it is followed by highly unusual email activity, like new inbox rules being created. Too many email security solutions focus on the inbox alone, but viewing these areas in a single scope is critical for security teams wanting to understand the full timeline of an incident. 

To this end, Darktrace creates a 360-degree view of each user and their behavior. This comprehensive view goes beyond native security monitoring tools, allowing security teams to identify instances of data exfiltration, human error, misdirected emails, inappropriate link sharing, unusual log activity, and more. 

In one real-life example, the security team saw an attack from both an email and a SaaS perspective to quickly understand the whole picture, thanks to Darktrace/Email and Darktrace/Apps™. 

Darktrace customers are getting significant value from this integrated security stack. “The whole suite of products has given us 100% visibility across our whole ecosystem, which is fantastic. A lot of times we need to use many products to do that, and with the Darktrace products, I have that all in one,” commented a vice president of enterprise security and fraud management at a major credit union. 

Siloed solutions are a massive pain point in the cyber industry. Most companies have several, layered tools in their security stacks. When there is little to no communication between them, the security team must contend with an inflated workload and misses out on value. They must learn how to navigate several different dashboards, translate between languages and terms, and manually correlate data, in addition to monitoring all the solutions daily. This process makes maintaining security more difficult for the team, especially in a threat landscape with increasingly complex and fast-paced attacks. 

By sending and collecting information to and from other tools that the security team already uses, whether they are a part of Darktrace’s product stack or not, Darktrace/Email optimizes workflows so security teams can reallocate resources to larger, more strategic projects.  

Collaborating Across Email Security and Cyber Risk Management Tools

Syncing email protections with cyber risk management tools even further reduces risk and hardens security.

When emails are received from domain names associated with the brand of the client, an attack surface management tool can automatically analyze if those domains should be included as part of the attack surface scope or trigger malicious domain responses. 

In the other direction, when the attack surface management tool identifies malicious assets, like suspicious domains, spoofing sites, and typo squatters, it can inform email security decisions. With integrations between tools, these malicious assets automatically become watched domains with heightened sensitivity for inbound email. 

This integrated risk reduction can occur internally as well. When security teams look at cyber risk from an internal perspective, they may identify attack paths and high value targets within the company’s digital estate. By leveraging this understanding, Darktrace can determine which employees are critical components of potential attack paths. Once determined, the AI can test them by creating phishing simulations using details like real-life communication patterns and calendar data. These tests generate insights that feed back into Darktrace/Email to harden the environment, for example by heightening sensitivity. 

This demonstrates the benefits of combining Darktrace/Email and Darktrace PREVENT™. As part of the Cyber AI Loop, these connections between email security and cyber risk management are made easy for the security team to understand and act on. One customer noted how this integration had improved its security team’s workflow.  

“The more you use of Darktrace, the better it can correlate on your behalf,” said a Chief Information Officer at a construction company. “That’s why we’re all in with Darktrace now. We now have a holistic Darktrace footprint, which benefits us because we have more of the modules working on our behalf and not having to do the correlations separately or in isolation.” 

Supporting Compatibility with External Security Solutions

Darktrace/Email also works together with external tools. In addition to its mature integration with email providers like Microsoft 365 and Google Workspaces, Darktrace/Email has an open architecture that makes it immensely flexible. It is both API-driven and compatible with syslog, so it can integrate with any security tool and feed into any SIEM or SOAR. 

This unlimited capacity for integration allows Darktrace to detect and respond to threats more precisely with access to more data, as well as reduce the security team’s time-to-meaning by putting all relevant information in a single pane of glass. 

Darktrace/Email is also part of the Darktrace Mobile App, so security teams can view notifications, reports, and remediation actions at any time, even on the go. In this way, Darktrace not only fits into the greater security posture, but also with employees’ day-to-day workflow. 

Finally, Darktrace/Email supports data exports. These translate and share the data it collects within the email environment, allowing the security team to communicate key takeaways generated by Darktrace/Email to anyone within the organization. It can export directly to Microsoft Excel, or any other data analytics tool. This is especially useful for security teams as they work with other departments like IT, compliance, finance, and more. 

Integrations Add Value to the Darktrace Partnership

While Darktrace/Email is a powerful tool on its own, a major source of its value comes from its compatibility with the rest of Darktrace, other tools, people, and processes. 

Deploying multiple Darktrace products builds a robust security ecosystem that enhances detection while breaking down silos and improving workflows, therefore enabling the security team to take on higher-level and more strategic work. By integrating with external tools, Darktrace not only increases its own value but also maximizes the return on investment of other security solutions a team already has.  

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
Dan Fein
VP, Product
Written by
Carlos Gray
Senior Product Marketing Manager, Email

Blog

/

/

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

/

/

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