Blog
/
Email
/
March 1, 2024

Navigating Email Security Gaps Beyond DMARC

Discover Darktrace's strategies for navigating email security gaps beyond DMARC. Enhance your defenses with advanced threat detection and mitigation.
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
Written by
Stephen Pickman
Senior Vice President, Engineering
Default blog image
01
Mar 2024

Email threat landscape  

Email has consistently ranked among the most targeted attack vectors, given its ubiquity and criticality to business operations. From September to December 2023, 10.4 million phishing emails were detected across Darktrace’s customer fleet demonstrating the frequency of attempted email-based attacks.

Businesses are searching for ways to harden their email security posture alongside email providers who are aiming to reduce malicious emails traversing their infrastructure, affecting their clients. Domain-based Message Authentication (DMARC) is a useful industry-wide protocol organizations can leverage to move towards these goals.  

What is DMARC?

DMARC is an email authentication protocol designed to enhance the security of email communication.

Major email service providers Google and Yahoo recently made the protocol mandatory for bulk senders in an effort to make inboxes safer worldwide. The new requirements demonstrate an increasing need for a standardized solution as misconfigured or nonexistent authentication systems continue to allow threat actors to evade detection and leverage the legitimate reputation of third parties.  

DMARC is a powerful tool that allows email administrators to confidently identify and stop certain spoofed emails; however, more organizations must implement the standard for it to reach its full potential. The success and effectiveness of DMARC is dependent on broad adoption of the standard – by organizations of all sizes.  

How does DMARC work?

DMARC builds on two key authentication technologies, Sender Policy Framework (SPF) and DomainKeys Identified Mail (DKIM) and helps to significantly improve their ability to prevent domain spoofing. SPF verifies that a sender’s IP address is authorized to send emails on behalf of a particular domain and DKIM ensures integrity of email content by providing a verifiable digital signature.  

DMARC adds to this by allowing domain owners to publish policies that set expectations for how SPF and DKIM verification checks relate to email addresses presented to users and whose authenticity the receiving mail server is looking to establish.  

These policies work in tandem to help authenticate email senders by verifying the emails are from the domain they say they are, working to prevent domain spoofing attacks. Key benefits of DMARC include:

  1. Phishing protection DMARC protects against direct domain spoofing in which a threat actor impersonates a legitimate domain, a common phishing technique threat actors use to trick employees to obtain sensitive information such as privileged credentials, bank information, etc.  
  2. Improving brand reputation: As DMARC helps to prevent impersonation of domains, it stands to maintain and increase an organization’s brand reputation. Additionally, as organizational reputation improves, so will the deliverability of emails.
  3. Increased visibility: DMARC provides enhanced visibility into email communication channels, including reports of all emails sent on behalf of your domain. This allows security teams to identify shadow-IT and any unauthorized parties using their domain.

Understanding DMARC’s Limitations

DMARC is often positioned as a way for organizations to ‘solve’ their email security problems, however, 65% of the phishing emails observed by Darktrace successfully passed DMARC verification, indicating that a significant number of threat actors are capable of manipulating email security and authentication systems in their exploits. While DMARC is a valuable tool in the fight against email-based attacks, the evolving threat landscape demands a closer look at its limitations.  

As threat actors continue to innovate, improving their stealth and evasion tactics, the number of attacks with valid DMARC authentication will only continue to increase in volume and sophistication. These can include:

  1. Phishing attacks that leverage non-spoofed domains: DMARC allows an organization to protect the domains that they own, preventing threat actors from being able to send phishing emails from their domains. However, threat actors will often create and use ‘look-a-like’ domains that closely resemble an organization’s domain to dupe users. 3% of the phishing emails identified by Darktrace utilized newly created domains, demonstrating shifting tactics.  
  2. Email Account Takeovers: If a threat actor gains access to a user’s email account through other social engineering means such as credential stuffing, they can then send phishing emails from the legitimate domain to pursue further attacks. Even though these emails are malicious, DMARC would not identify them as such because they are coming from an authorized domain or sender.  

Organizations must also ensure their inbound analysis of emails is not skewed by successful DMARC authentication. Security teams cannot inherently trust emails that pass DMARC, because the source cannot always be legitimized, like in the event of an account takeover. If a threat actor gains access to an authenticated email account, emails sent by the threat actor from that account will pass DMARC – however the contents of that email may be malicious. Sender behavior must be continuously evaluated and vetted in real time as past communication history and validated DMARC cannot be solely relied upon amid an ever-changing threat landscape.  

Security teams should lean on other security measures, such as anomaly detection tools that can identify suspicious emails without relying on historical attack rules and static data. While DMARC is not a silver bullet for email security, it is nevertheless foundational in helping organizations protect their brand identity and must be viewed as an essential layer in an organization's overall cyber security strategy.  

Implementing DMARC

Despite the criticality of DMARC for preserving brand reputation and trust, adoption of the standard has been inconsistent. DMARC can be complex to implement with many organizations lacking the time required to understand and successfully implement the standard. Because of this, DMARC set-up is often outsourced, giving security and infrastructure teams little to no visibility into or control of the process.  

Implementation of DMARC is only the start of this process, as DMARC reports must be consistently monitored to ensure organizations have visibility into who is sending mail from their domain, the volume of mail being sent and whether the mail is passing authentication protocols. This process can be time consuming for security teams who are already faced with mounting responsibilities, tight budgets, and personnel shortages. These complexities unfortunately delay organizations from using DMARC – especially as many today still view it as a ‘nice to have’ rather than an essential.  

With the potential complexities of the DMARC implementation process, there are many ways security and infrastructure teams can still successfully roll out the standard. Initial implementation should start with monitoring, policy adjustment and then enforcement. As business changes over time, DMARC should be reviewed regularly to ensure ongoing protection and maintain domain reputation.

The Future of Email Security

As email-based attacks continue to rise, the industry must recognize the importance of driving adoption of foundational email authentication protocols. To do this, a new and innovative approach to DMARC is needed. DMARC products must evolve to better support organizations throughout the ongoing DMARC monitoring process, rather than just initial implementation. These products must also be able to share intelligence across an organization’s security stack, extending beyond email security tools. Integration across these products and tools will help organizations optimize their posture, ensuring deep understanding of their domain and increased visibility across the entire enterprise.

DMARC is critical in protecting brand identity and mitigating exact-domain based attacks. However, organizations must understand DMARC’s unique benefits and limitations to ensure their inboxes are fully protected. In today’s evolving threat landscape, organizations require a robust, multi-layered approach to stop email threats – in inbound mail and beyond. Email threats have evolved – its time security does too.

Join Darktrace on 9 April for a virtual event to explore the latest innovations needed to get ahead of the rapidly evolving threat landscape. Register today to hear more about our latest innovations coming to Darktrace’s offerings. For additional insights check out Darktrace’s 2023 End of Year Threat Report.

Credit to Carlos Gray and Stephen Pickman for their contribution to this blog

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
Written by
Stephen Pickman
Senior Vice President, Engineering

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