October 30, 2023

Exploring AI Threats: Package Hallucination Attacks

Learn how malicious actors exploit errors in generative AI tools to launch packet attacks. Read how Darktrace products detect and prevent these threats!

Written by

Charlotte Thompson

Cyber Analyst

Written by

Tiana Kelly

Deputy Team Lead, London & Cyber Analyst

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

Charlotte Thompson

Cyber Analyst

Written by

Tiana Kelly

Deputy Team Lead, London & Cyber Analyst

Oct 2023

AI tools open doors for threat actors

On November 30, 2022, the free conversational language generation model ChatGPT was launched by OpenAI, an artificial intelligence (AI) research and development company. The launch of ChatGPT was the culmination of development ongoing since 2018 and represented the latest innovation in the ongoing generative AI boom and made the use of generative AI tools accessible to the general population for the first time.

ChatGPT is estimated to currently have at least 100 million users, and in August 2023 the site reached 1.43 billion visits [1]. Darktrace data indicated that, as of March 2023, 74% of active customer environments have employees using generative AI tools in the workplace [2].

However, with new tools come new opportunities for threat actors to exploit and use them maliciously, expanding their arsenal.

Much consideration has been given to mitigating the impacts of the increased linguistic complexity in social engineering and phishing attacks resulting from generative AI tool use, with Darktrace observing a 135% increase in ‘novel social engineering attacks’ across thousands of active Darktrace/Email™ customers from January to February 2023, corresponding with the widespread adoption of ChatGPT and its peers [3].

Less overall consideration, however, has been given to impacts stemming from errors intrinsic to generative AI tools. One of these errors is AI hallucinations.

What is an AI hallucination?

AI “hallucination” is a term which refers to the predictive elements of generative AI and LLMs’ AI model gives an unexpected or factually incorrect response which does not align with its machine learning training data [4]. This differs from regular and intended behavior for an AI model, which should provide a response based on the data it was trained upon.

Why are AI hallucinations a problem?

Despite the term indicating it might be a rare phenomenon, hallucinations are far more likely than accurate or factual results as the AI models used in LLMs are merely predictive and focus on the most probable text or outcome, rather than factual accuracy.

Given the widespread use of generative AI tools in the workplace employees are becoming significantly more likely to encounter an AI hallucination. Furthermore, if these fabricated hallucination responses are taken at face value, they could cause significant issues for an organization.

Use of generative AI in software development

Software developers may use generative AI for recommendations on how to optimize their scripts or code, or to find packages to import into their code for various uses. Software developers may ask LLMs for recommendations on specific pieces of code or how to solve a specific problem, which will likely lead to a third-party package. It is possible that packages recommended by generative AI tools could represent AI hallucinations and the packages may not have been published, or, more accurately, the packages may not have been published prior to the date at which the training data for the model halts. If these hallucinations result in common suggestions of a non-existent package, and the developer copies the code snippet wholesale, this may leave the exchanges vulnerable to attack.

Research conducted by Vulcan revealed the prevalence of AI hallucinations when ChatGPT is asked questions related to coding. After sourcing a sample of commonly asked coding questions from Stack Overflow, a question-and-answer website for programmers, researchers queried ChatGPT (in the context of Node.js and Python) and reviewed its responses. In 20% of the responses provided by ChatGPT pertaining to Node.js at least one un-published package was included, whilst the figure sat at around 35% for Python [4].

Hallucinations can be unpredictable, but would-be attackers are able to find packages to create by asking generative AI tools generic questions and checking whether the suggested packages exist already. As such, attacks using this vector are unlikely to target specific organizations, instead posing more of a widespread threat to users of generative AI tools.

Malicious packages as attack vectors

Although AI hallucinations can be unpredictable, and responses given by generative AI tools may not always be consistent, malicious actors are able to discover AI hallucinations by adopting the approach used by Vulcan. This allows hallucinated packages to be used as attack vectors. Once a malicious actor has discovered a hallucination of an un-published package, they are able to create a package with the same name and include a malicious payload, before publishing it. This is known as a malicious package.

Malicious packages could also be recommended by generative AI tools in the form of pre-existing packages. A user may be recommended a package that had previously been confirmed to contain malicious content, or a package that is no longer maintained and, therefore, is more vulnerable to hijack by malicious actors.

In such scenarios it is not necessary to manipulate the training data (data poisoning) to achieve the desired outcome for the malicious actor, thus a complex and time-consuming attack phase can easily be bypassed.

An unsuspecting software developer may incorporate a malicious package into their code, rendering it harmful. Deployment of this code could then result in compromise and escalation into a full-blown cyber-attack.

Figure 1: Flow diagram depicting the initial stages of an AI Package Hallucination Attack.

For providers of Software-as-a-Service (SaaS) products, this attack vector may represent an even greater risk. Such organizations may have a higher proportion of employed software developers than other organizations of comparable size. A threat actor, therefore, could utilize this attack vector as part of a supply chain attack, whereby a malicious payload becomes incorporated into trusted software and is then distributed to multiple customers. This type of attack could have severe consequences including data loss, the downtime of critical systems, and reputational damage.

How could Darktrace detect an AI Package Hallucination Attack?

In June 2023, Darktrace introduced a range of DETECT™ and RESPOND™ models designed to identify the use of generative AI tools within customer environments, and to autonomously perform inhibitive actions in response to such detections. These models will trigger based on connections to endpoints associated with generative AI tools, as such, Darktrace’s detection of an AI Package Hallucination Attack would likely begin with the breaching of one of the following DETECT models:

Compliance / Anomalous Upload to Generative AI
Compliance / Beaconing to Rare Generative AI and Generative AI
Compliance / Generative AI

Should generative AI tool use not be permitted by an organization, the Darktrace RESPOND model ‘Antigena / Network / Compliance / Antigena Generative AI Block’ can be activated to autonomously block connections to endpoints associated with generative AI, thus preventing an AI Package Hallucination attack before it can take hold.

Once a malicious package has been recommended, it may be downloaded from GitHub, a platform and cloud-based service used to store and manage code. Darktrace DETECT is able to identify when a device has performed a download from an open-source repository such as GitHub using the following models:

Device / Anomalous GitHub Download
Device / Anomalous Script Download Followed By Additional Packages

Whatever goal the malicious package has been designed to fulfil will determine the next stages of the attack. Due to their highly flexible nature, AI package hallucinations could be used as an attack vector to deliver a large variety of different malware types.

As GitHub is a commonly used service by software developers and IT professionals alike, traditional security tools may not alert customer security teams to such GitHub downloads, meaning malicious downloads may go undetected. Darktrace’s anomaly-based approach to threat detection, however, enables it to recognize subtle deviations in a device’s pre-established pattern of life which may be indicative of an emerging attack.

Subsequent anomalous activity representing the possible progression of the kill chain as part of an AI Package Hallucination Attack could then trigger an Enhanced Monitoring model. Enhanced Monitoring models are high-fidelity indicators of potential malicious activity that are investigated by the Darktrace analyst team as part of the Proactive Threat Notification (PTN) service offered by the Darktrace Security Operation Center (SOC).

Conclusion

Employees are often considered the first line of defense in cyber security; this is particularly true in the face of an AI Package Hallucination Attack.

As the use of generative AI becomes more accessible and an increasingly prevalent tool in an attacker’s toolbox, organizations will benefit from implementing company-wide policies to define expectations surrounding the use of such tools. It is simple, yet critical, for example, for employees to fact check responses provided to them by generative AI tools. All packages recommended by generative AI should also be checked by reviewing non-generated data from either external third-party or internal sources. It is also good practice to adopt caution when downloading packages with very few downloads as it could indicate the package is untrustworthy or malicious.

As of September 2023, ChatGPT Plus and Enterprise users were able to use the tool to browse the internet, expanding the data ChatGPT can access beyond the previous training data cut-off of September 2021 [5]. This feature will be expanded to all users soon [6]. ChatGPT providing up-to-date responses could prompt the evolution of this attack vector, allowing attackers to publish malicious packages which could subsequently be recommended by ChatGPT.

It is inevitable that a greater embrace of AI tools in the workplace will be seen in the coming years as the AI technology advances and existing tools become less novel and more familiar. By fighting fire with fire, using AI technology to identify AI usage, Darktrace is uniquely placed to detect and take preventative action against malicious actors capitalizing on the AI boom.

Credit to Charlotte Thompson, Cyber Analyst, Tiana Kelly, Analyst Team Lead, London, Cyber Analyst

References

[1] https://seo.ai/blog/chatgpt-user-statistics-facts

[2] https://darktrace.com/news/darktrace-addresses-generative-ai-concerns

[3] https://darktrace.com/news/darktrace-email-defends-organizations-against-evolving-cyber-threat-landscape

[4] https://vulcan.io/blog/ai-hallucinations-package-risk?nab=1&utm_referrer=https%3A%2F%2Fwww.google.com%2F

[5] https://twitter.com/OpenAI/status/1707077710047216095

[6] https://www.reuters.com/technology/openai-says-chatgpt-can-now-browse-internet-2023-09-27/

Deputy Team Lead, London & Cyber Analyst

Inside the SOC

Written by

Charlotte Thompson

Cyber Analyst

Written by

Tiana Kelly

Deputy Team Lead, London & Cyber Analyst

•

February 13, 2026

Emma Foulger

Global Threat Research Operations Lead

•

February 13, 2026

Amel Edmond

Chief Information Officer

Watch the NIS2 Webinar

Blog

February 13, 2026

CVE-2026-1731: How Darktrace Sees the BeyondTrust Exploitation Wave Unfolding

Note: Darktrace's Threat Research team is publishing now to help defenders. We will update continue updating this blog as our investigations unfold.

Background

On February 6, 2026, the Identity & Access Management solution BeyondTrust announced patches for a vulnerability, CVE-2026-1731, which enables unauthenticated remote code execution using specially crafted requests. This vulnerability affects BeyondTrust Remote Support (RS) and particular older versions of Privileged Remote Access (PRA) [1].

A Proof of Concept (PoC) exploit for this vulnerability was released publicly on February 10, and open-source intelligence (OSINT) reported exploitation attempts within 24 hours [2].

Previous intrusions against Beyond Trust technology have been cited as being affiliated with nation-state attacks, including a 2024 breach targeting the U.S. Treasury Department. This incident led to subsequent emergency directives from the Cybersecurity and Infrastructure Security Agency (CISA) and later showed attackers had chained previously unknown vulnerabilities to achieve their goals [3].

Additionally, there appears to be infrastructure overlap with React2Shell mass exploitation previously observed by Darktrace, with command-and-control (C2) domain avg.domaininfo[.]top seen in potential post-exploitation activity for BeyondTrust, as well as in a React2Shell exploitation case involving possible EtherRAT deployment.

Darktrace Detections

Darktrace’s Threat Research team has identified highly anomalous activity across several customers that may relate to exploitation of BeyondTrust since February 10, 2026. Observed activities include:

- Outbound connections and DNS requests for endpoints associated with Out-of-Band Application Security Testing; these services are commonly abused by threat actors for exploit validation. Associated Darktrace models include:

o Compromise / Possible Tunnelling to Bin Services
‍

- Suspicious executable file downloads. Associated Darktrace models include:

o Anomalous File / EXE from Rare External Location
‍

- Outbound beaconing to rare domains. Associated Darktrace models include:

o Compromise / Agent Beacon (Medium Period)

o Compromise / Agent Beacon (Long Period)

o Compromise / Sustained TCP Beaconing Activity To Rare Endpoint

o Compromise / Beacon to Young Endpoint

o Anomalous Server Activity / Rare External from Server

o Compromise / SSL Beaconing to Rare Destination
‍

- Unusual cryptocurrency mining activity. Associated Darktrace models include:

o Compromise / Monero Mining

o Compromise / High Priority Crypto Currency Mining

‍‍

And model alerts for:

o Compromise / Rare Domain Pointing to Internal IP

‍

IT Defenders: As part of best practices, we highly recommend employing an automated containment solution in your environment. For Darktrace customers, please ensure that Autonomous Response is configured correctly. More guidance regarding this activity and suggested actions can be found in the Darktrace Customer Portal.

‍

Appendices

Potential indicators of post-exploitation behavior:

· 217.76.57[.]78 – IP address - Likely C2 server

· hXXp://217.76.57[.]78:8009/index.js - URL - Likely payload

· b6a15e1f2f3e1f651a5ad4a18ce39d411d385ac7 - SHA1 - Likely payload

· 195.154.119[.]194 – IP address – Likely C2 server

· hXXp://195.154.119[.]194/index.js - URL – Likely payload

· avg.domaininfo[.]top – Hostname – Likely C2 server

· 104.234.174[.]5 – IP address - Possible C2 server

· 35da45aeca4701764eb49185b11ef23432f7162a – SHA1 – Possible payload

· hXXp://134.122.13[.]34:8979/c - URL – Possible payload

· 134.122.13[.]34 – IP address – Possible C2 server

· 28df16894a6732919c650cc5a3de94e434a81d80 - SHA1 - Possible payload

References:

1. https://nvd.nist.gov/vuln/detail/CVE-2026-1731

2. https://www.securityweek.com/beyondtrust-vulnerability-targeted-by-hackers-within-24-hours-of-poc-release/

3. https://www.rapid7.com/blog/post/etr-cve-2026-1731-critical-unauthenticated-remote-code-execution-rce-beyondtrust-remote-support-rs-privileged-remote-access-pra/

‍

About the author

Emma Foulger

Global Threat Research Operations Lead

Blog

AI

February 13, 2026

How AI is redefining cybersecurity and the role of today’s CIO

Why AI is essential to modern security

As attackers use automation and AI to outpace traditional tools and people, our approach to cybersecurity must fundamentally change. That’s why one of my first priorities as Withum's CIO was to elevate cybersecurity from a technical function to a business enabler.

What used to be “IT’s problem” is now a boardroom conversation – and for good reason. Protecting our data, our people, and our clients directly impacts revenue, reputation and competitive positioning.

As CIOs / CISOs, our responsibilities aren’t just keeping systems running, but enabling trust, protecting our organization's reputation, and giving the business confidence to move forward even as the digital world becomes less predictable. To pull that off, we need to know the business inside-out, understand risk, and anticipate what's coming next. That's where AI becomes essential.

Staying ahead when you’re a natural target

With more than 3,100 team members and over 1,000 CPAs (Certified Public Accountant), Withum’s operates in an industry that naturally attracts attention from attackers. Firms like ours handle highly sensitive financial and personal information, which puts us squarely in the crosshairs for sophisticated phishing, ransomware, and cloud-based attacks.

We’ve built our security program around resilience, visibility, and scale. By using Darktrace’s AI-powered platform, we can defend against both known and unknown threats, across email and network, without slowing our teams down.

Our focus is always on what we’re protecting: our clients’ information, our intellectual property, and the reputation of the firm. With Darktrace, we’re not just keeping up with the massive volume of AI-powered attacks coming our way, we’re staying ahead. The platform defends our digital ecosystem around the clock, detecting potential threats across petabytes of data and autonomously investigating and responding to tens of thousands of incidents every year.

Catching what traditional tools miss

Beyond the sheer scale of attacks, Darktrace ActiveAI Security PlatformTM is critical for identifying threats that matter to our business. Today’s attackers don’t use generic techniques. They leverage automation and AI to craft highly targeted attacks – impersonating trusted colleagues, mimicking legitimate websites, and weaving in real-world details that make their messages look completely authentic.

The platform, covering our network, endpoints, inboxes, cloud and more is so effective because it continuously learns what’s normal for our business: how our users typically behave, the business- and industry-specific language we use, how systems communicate, and how cloud resources are accessed. It picks up on minute details that would sail right past traditional tools and even highly trained security professionals.

Freeing up our team to do what matters

On average, Darktrace autonomously investigates 88% of all our security events, using AI to connect the dots across email, network, and cloud activity to figure out what matters. That shift has changed how our team works. Instead of spending hours sorting through alerts, we can focus on proactive efforts that actually strengthen our security posture.

For example, we saved 1,850 hours on investigating security issues over a ten-day period. We’ve reinvested the time saved into strengthening policies, refining controls, and supporting broader business initiatives, rather than spending endless hours manually piecing together alerts.

Real confidence, real results

The impact of our AI-driven approach goes well beyond threat detection. Today, we operate from a position of confidence, knowing that threats are identified early, investigated automatically, and communicated clearly across our organization.

That confidence was tested when we withstood a major ransomware attack by a well-known threat group. Not only were we able to contain the incident, but we were able to trace attacker activity and provided evidence to law enforcement. That was an exhilarating experience! My team did an outstanding job, and moments like that reinforce exactly why we invest in the right technology and the right people.

Internally, this capability has strengthened trust at the executive level. We share security reporting regularly with leadership, translating technical activity into business-relevant insights. That transparency reinforces cybersecurity as a shared responsibility, one that directly supports growth, continuity, and reputation.

Culturally, we’ve embedded security awareness into daily operations through mandatory monthly training, executive communication, and real-world industry examples that keep cybersecurity top of mind for every employee.

The only headlines we want are positive ones: Withum expanding services, Withum growing year over year. Security plays a huge role in making sure that’s the story we get to tell.

What’s next

Looking ahead, we’re expanding our use of Darktrace, including new cloud capabilities that extend AI-driven visibility and investigation into our AWS and Azure environments.

As I continue shaping our security team, I look for people with passion, curiosity, and a genuine drive to solve problems. Those qualities matter just as much as formal credentials in my view. Combined with AI, these attributes help us build a resilient, engaged security function with low turnover and high impact.

For fellow technology leaders, my advice is simple: be forward-thinking and embrace change. We must understand the business, the threat landscape, and how technology enables both. By augmenting human expertise rather than replacing it, AI allows us to move upstream by anticipating risk, advising the business, and fostering stronger collaboration across teams.

‍

About the author

Amel Edmond

Chief Information Officer

Your data. Our AI.

Elevate your network security with Darktrace AI

Get a demo

Check out this article by Darktrace: Exploring AI Threats: Package Hallucination Attacks

Exploring AI Threats: Package Hallucination Attacks

AI tools open doors for threat actors

What is an AI hallucination?

Why are AI hallucinations a problem?

Use of generative AI in software development

Malicious packages as attack vectors

How could Darktrace detect an AI Package Hallucination Attack?

Conclusion

References

CVE-2026-1731: How Darktrace Sees the BeyondTrust Exploitation Wave Unfolding

How AI is redefining cybersecurity and the role of today’s CIO

Enjoying the blog?

More in this series

How AI is redefining cybersecurity and the role of today’s CIO

The State of AI Cybersecurity 2026: Unveiling insights from over 1,500 security leaders

Introducing Darktrace / SECURE AI: Complete AI Security Across Your Enterprise

Blog

February 13, 2026

CVE-2026-1731: How Darktrace Sees the BeyondTrust Exploitation Wave Unfolding

Background

Darktrace Detections

Appendices

Potential indicators of post-exploitation behavior:

References:

Blog

AI

February 13, 2026

How AI is redefining cybersecurity and the role of today’s CIO

Why AI is essential to modern security

Staying ahead when you’re a natural target

Catching what traditional tools miss

Freeing up our team to do what matters

Real confidence, real results

What’s next