© Dave Sanders for The New York Times
© Emmanuel Polanco
© Manuel Orbegozo for The New York Times
© Dave Sanders for The New York Times
© Manuel Orbegozo for The New York Times
© The New York Times
© Lucas Foglia for The New York Times
© Dave Sanders for The New York Times
Are you a cybersecurity professional, researcher, CISO or industry expert with insights to share? The Cyber Express is always looking to bring new voices and perspectives to the cybersecurity community.
If you would like to be featured on Security Pill or discuss a potential podcast collaboration, reach out to us at [samiksha.jain@thecyberexpress.com].
Have a story, expertise, or perspective to share? Let’s start the conversation.
© Eric Helgas for The New York Times
Apart from the privacy concerns around smart glasses, researchers have found that some cheap brands come with barely any security at all.
ABC Australia reports that researchers from NSB Cyber and Abstract Shield tested two inexpensive pairs, costing A$60 and A$110 (around US$42 and US$78), and found more than a dozen flaws across the smart glasses themselves, their app, and an associated website.
The main problem they uncovered was insecure Bluetooth pairing: If the glasses were powered on and not connected to their owner’s phone, an attacker could connect first, with no password or meaningful pairing confirmation.
After connecting, an attacker could reportedly control the glasses to capture photos or recordings, copy existing media, and intercept data moving between the glasses and the phone. An attacker could also make another device appear to be the victim’s glasses, allowing it to connect to the owner’s mobile app.
The testing also found that a Bluetooth-visible device identifier could allegedly be used with a weakness in the app’s website to retrieve a user’s email address and date of birth.
The research uncovered another privacy issue. ABC reports that voice or text submitted to the built-in AI, along with images sent to it, was first transmitted to a server in Shenzhen and could be forwarded elsewhere, depending on the function. The tests did not establish how the data was subsequently used.
The server locations, combined with some of the AI’s answers to specific questions, led researchers to conclude that the chatbot companion relied at least in part on Chinese sovereign AI models. Professor Kimberlee Weatherall, a technology regulation expert involved in the testing, said the failure to identify China in the privacy policy appeared to violate the Australian Privacy Principles,
The timing of the testing is also relevant because Australia’s smart-device security standards apply to most consumer smart devices manufactured on or after March 4, 2026. They require, among other measures, no universal default passwords, a way to report vulnerabilities, and information about the minimum security-update period. Devices made before that date are outside the requirements.
Experts quoted by ABC said the devices violated Australia’s privacy laws and were also likely to breach several sections of the Cyber Security Act. However, whether the new smart-device standards apply would depend partly on when the glasses were manufactured, and the rules have not yet been tested in a known enforcement action.
Professor Weatherall said:
“The rules say that the password must be unique. It doesn’t even seem like they were applying a password, which might mean that their standards are so low they don’t even technically breach that rule, which I find amazing.”
We’re not fans of smart glasses, expensive or cheap. But if you own a pair:
From reporting threats to removing them.
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Passkeys are a fantastic technology. Since they are bound to the site they are created for, they cannot be phished by a hacker’s fake login screen. If a site suffers a data breach, passkeys are asymmetric and cannot be recovered from the server-side details.
This leads to passkeys being the perfect fit for a corporate environment, but a poor fit for personal security. To an individual, the greatest risks are instead permanent account lockout, automated account bans, and device loss. By using passkeys, you gain better security against man-in-the-middle attacks but face the higher probability scenario of losing access to your accounts.
Phishing through the standard login flow is eliminated by passkeys, but it creates a false sense of security. An account’s security is still dictated by the weakest recovery method: SMS, email links, security questions, and so on. If these recovery methods aren’t enabled, then the risk of permanent lockout remains for the user.
↫ Ethan Hawksley
I’ve always felt something was off about passkeys, and have never used them. They’ve become – or were always intended to be – tools for further lock-in by especially Google and Apple, tying their entire usage flow to their respective operating systems. They also don’t seem to work well if you often work on devices not your own, which is a major hassle. None of these shortcomings come into play when using a traditional password manager, even if they require more manual work.
Just let me use a password manager with random password generation, instead of trying to force passkeys down my throat.
© Andria Lo for The New York Times
© Manuel Orbegozo for The New York Times
© Jeff Chiu/Associated Press
© Matt Chinworth
© Brian Stauffer
With doomsday AI scenarios dominating the news, lawmakers are rightly concerned about reports concerning security breaches at major US AI labs, such as the OpenAI–Hugging Face incident and the many others reported in its aftermath. As they consider potentially regulating frontier AI, they should focus any new legislation on the immediate, demonstrated risks from those incidents.
Post-incident reports show that the Hugging Face incident could have been mitigated or prevented by following longstanding cybersecurity best practices, like stronger sandboxing and monitoring. Any new legislation should focus on closing gaps in existing law to prevent AI companies from taking unreasonable risks with the public's security.
ensure ai serves people, not power
When an AI developer or deployer runs a test or a task that has a high likelihood of causing harm to third parties—for instance, by breaking into someone else's computers—there should be clear minimum safety requirements. Such tests should run in a properly sandboxed test environment, disconnected from other systems, and be monitored and logged. Following these fundamental best practices would have prevented or substantially mitigated all of the incidents at AI labs that we currently know about.
That said, any proposal must be flexible enough to evolve with changing technology. Minimum safety requirements specific only to current AI technologies are likely to become obsolete; legal standards tied to well-established cybersecurity best practices are far more likely to stand the test of time. Tying any new mandates to evidence-backed security protocols also protects the public without impeding future AI development.
Strong legislation should also mandate and fund independent third-party investigations into any serious security incidents that may occur during AI labs’ tests of new tools, and make reports of these investigations available to the public. This important transparency measure would go a long way toward providing public oversight of the industry.
As with any technology regulation, those targeting cybersecurity practices at AI labs must be careful, precise, and practical.
© Gabby Jones/Bloomberg
© Lucas Foglia for The New York Times
© Brendan Mcdermid/Reuters
Two things happened last week, one day apart, and almost nobody connected them. On 11 September, the EU Cyber Resilience Act’s vulnerability reporting obligations came into force. Companies covered by the regulation now have to report actively exploited vulnerabilities within 24 hours and provide a fuller notification within 72. On 12 September, Anthropic CEO Dario […]
The post Slow is a design principle, not a delay appeared first on Heimdal Security Blog.
© Jun Cen
© Lucas Foglia for The New York Times
© Priyanshu Singh/Reuters
© Ludovic Marin/Agence France-Presse — Getty Images
© Jason Henry for The New York Times
© Jun Cen
In August, Cliff Stoll gave a talk at DEF CON, remembering the wily hacker he stalked forty years ago.
Great fun.
The term “digital sovereignty” has become ubiquitous. European officials invoke it in debates about cloud infrastructure, AI, semiconductors, and platform regulation. Governments throughout the global majority use it to argue for greater control over data and communications infrastructure and boost their economies. Companies market “sovereign cloud” products designed to reassure their customers that their information stays under local jurisdiction. But digital sovereignty could be something more: an opportunity for users around the world to build more resilient, open systems and the skills and infrastructure to maintain them.
There is no singular definition of digital sovereignty, nor is there a single coherent position in the digital rights space. Despite its growing popularity, the term remains frustratingly vague. Policymakers, regulators, civil society groups, and others can mean very different things when they use the term. But to start simply with a broad definition, we can say that it means having the capacity to control one’s digital destiny—though the implications of that will obviously differ considerably whether you’re talking about an individual or a country.
We can start by developing a shared understanding of what digital sovereignty actually means. We’ve also included a glossary of terms at the bottom of this post.
In Europe and other places where digital sovereignty has become a topic of policy, discussions focus on reducing dependency: on foreign (and particularly American) cloud infrastructure, chips, platforms, and at times, foreign political priorities. The concern is both economic and geopolitical. If essential infrastructure is controlled by companies elsewhere—and thus subject to the laws of another jurisdiction—then what control does a country actually have over its own digital future?
In global majority countries in particular, wars, sanctions, and the growing fragmentation of the internet have demonstrated for many that the physical infrastructure that underlies digital life is neither neutral nor invulnerable.
Amidst this increasing geopolitical instability governments and civil society should consider whether digital sovereignty can help shore up that infrastructure.
A recent Franco-German joint paper on digital sovereignty defines it as the “capability and capacity to develop, provide, use, adapt and control digital technologies including hardware in an independent, self-determined and secure manner” and puts forward a framework to operationalize Europe’s capacity to act in the digital domain.
Some governments, such as Germany’s, have started to put funding behind sovereignty efforts through initiatives like the Sovereign Tech Agency, which “invest[s] globally in the open software components that underpin Germany's and Europe's competitiveness and ability to innovate.”
Positions on digital sovereignty among EFF’s allies across Europe vary. Open Rights Group have defined digital sovereignty as “the ability of a country to have control over its digital infrastructure, data, and technology” and states it to be “critical for the UK’s economic and national security.”
Similarly, the European Partnership for Democracy has expressed concern that “a few Big Tech corporations decide our collective destiny,” and argue that the EU should explore “alternative ownership models for tech companies and clearly [define] their purpose and mission.” And our friends at EDRi (of which EFF is a member) have stated clearly that “Europe’s digital sovereignty starts with open source.” Some initiatives, such as DI.DAY, consider digital sovereignty an opportunity to free users from Big Tech dependencies.
Elsewhere in the world, conversations about digital sovereignty often take a different shape. Indigenous discussions of the topic have been ongoing for more than a decade and focus on the inherent right of Native nations to govern their own digital ecosystems. In Southeast Asia, the desire for digital sovereignty has created growth in the sovereign cloud industry, but the conversation isn’t purely economic: Concerns about jurisdiction for where data is held are driving much of the conversation.
In Latin America, digital public infrastructure is often a key aspect of debates. Across Africa, leaders speak of a desire to shift the continent from being consumers of technology to becoming architects of their own digital infrastructure and data ecosystems. And in the Middle East and North Africa, concerns about reliance on U.S. technology companies—which have engaged in conflict and disproportionate censorship (particularly of Palestinian voices) in the region—are often paramount.
Reem Almasri, a senior researcher based in Jordan, recently spoke to EFF about digital sovereignty, which she sees as “the ability of people and communities to choose, control, and use technology that serves their needs and values,” particularly in light of the role that U.S. companies have played in regional conflicts.
In a January article, Almasri pointed to growing concerns about granting greater sovereignty and influence to governments over citizens’ data, communications, and websites, writing: “This is particularly worrisome in countries that impose high levels of internet and media censorship and run unaccountable surveillance programs on their citizens’ data.”
Indeed, while pushing for greater sovereignty from Big Tech has benefits, there is an inherent risk that some states will pursue digital sovereignty as a means of cutting off or splintering access—as we’ve already seen in Iran, Russia, and elsewhere.
For that reason, it’s no surprise that some, such as Iranian professor Azadeh Akbari, believe that “the current wave pushing digital sovereignty as the key to ending dependency on American and Chinese technology is negligent of its Eurocentric bias.”
In a world where people have digital sovereignty, civil society should be able to communicate freely, privately, and anonymously if they wish. People should be able to easily understand where their data lives and who has access to it. That data should be easily portable between platforms and services.
At EFF, we view digital sovereignty not as a walled garden, but as an opportunity for resilience and development of industries and skills. We believe that governments can and should take a role in crafting digital sovereignty that centers the autonomy of users rather than just re-creating a state of digital dependency with a new set of companies. Governments should support and use free and open source tools and projects built using principles of interoperability and data portability. This support should include employing full-time developers, UX designers, and community managers. Government policy and legislation should grant users control of their own data and a clear understanding of who can lawfully access it. Digital sovereignty should foster users’ ability to choose how they use digital products and services, free from unfair lock-ins, coercive terms and manipulative defaults. It should also foster the broader public interest internet, the part of the web that provides public goods and useful services without requiring the scale or the business practices of the tech giants.
Encryption backdoors are fundamentally incompatible with a vision of data sovereignty that centers user control. Governments should support the development and normalization of reputable end-to-end encrypted communications as well as strong encryption for data at rest. This support should include employing cryptographers and contributing to strong, peer-reviewed encryption standards strengthened by data minimization as a fundamental design principle, as well as refraining from legislating mandates for “lawful access” or any other reason.
As technologists, we don’t have to wait for governments to act in order to create the digital sovereignty we want. We get the internet that we build. We can contribute to open source, decentralized, and end-to-end encrypted projects. We can build standards that make interoperability and data portability a feature from the very beginning. We can resist the call of proprietary solutions, user lock-in, and encryption backdoors.
And finally, while digital sovereignty is often framed as a response to the dominance of Big Tech, that does not mean that there is no role for private companies to play. There is no point in replacing the influence of a few mostly US-based tech companies with a handful of giants based elsewhere. Companies can and should build platforms and services on top of open source, decentralized protocols and contribute to the ecosystem. Companies should also minimize processing a person’s data except as strictly necessary to provide them what they asked for, and only with opt-in consent that makes it clear to users what data they are gathering, where it is stored, and who has access to it. And companies should build their tools and platforms in a way that allows interoperability and that makes it easy for users to leave with their data. Some of these practices are already required by law in some jurisdictions, but companies don’t have to merely do the bare minimum the law demands: they should respect their users and support data sovereignty right now.
The following terms are useful for understanding this blog post as well as the broader conversation about Digital Sovereignty:
Intermediary liability: the legal responsibility of online service providers (ISPs, websites, social media platforms) for unlawful activities by their users, such as defamation, copyright infringement, or illegal hate speech.
The stack: a secure, open-source technology framework, often focusing on European alternatives, designed to break dependencies on (mostly) US-based technology providers. It comprises interoperable, vendor-neutral, and transparent digital infrastructures designed to regain control over data, infrastructure, and technology.
Digital sovereignty: the ability of people, as nations, organizations, and individuals, to control their own digital destiny by retaining authority over their own data, technology, and infrastructure.
Data sovereignty: the principle that digital information is subject to the laws and governance frameworks of the country or region where it is physically collected, stored, or processed. It dictates that data remains bound by the specific privacy protections and regulations of its originating jurisdiction, regardless of where the collecting organization is located.
Digital commons: a shared, online resource, such as knowledge, software, and data, that is collectively produced, governed, and maintained by a community, intended for public access. Examples include Wikipedia, open source operating systems such as Linux, and Creative Commons licensed content.
Data portability/interoperability: the ability to easily transfer personal data from one service provider to another, or to a personal system, in a structured, machine-readable format. It empowers users to move away from "walled gardens," reducing vendor lock-in and enhancing user autonomy.
Digital dependency: the opposite of digital sovereignty. The inability of people as nations, organizations, and individuals to control their own digital destiny through control over their own data, technology, and infrastructure.
Decentralization: a shift away from relying on centralized, often US-based, corporate platforms toward a distributed, user-centric internet where individuals, communities, and nations maintain control over their data, digital identity, and infrastructure.
End-to-end encryption (e2ee): a secure communication process where only the sender and intended recipient can access, read, or decrypt messages or data.
Fairness (à la the Digital Fairness Act): the absence of deceptive, manipulative, or addictive design practices that distort consumer choice and exploit vulnerabilities.
User sovereignty: the concept that individuals possess absolute control over their personal data, digital identity, and online privacy, rejecting the centralization of power by large technology platforms. It emphasizes user consent, decentralization, and the ability to manage personal data using secure and independent tools.
© Lucas Foglia for The New York Times
Check Point Research disclosed Tuesday that a weakness in ChatGPT's code-execution sandbox let data from one user's connected Gmail account be moved into a separate, attacker-controlled ChatGPT account, with no confirmation prompt shown to the victim.
The flaw sat not in the model but in the infrastructure beneath it. Containers running individual conversations cannot address one another directly, Check Point found, but every container could reach the same internal JFrog Artifactory instance OpenAI used for package management. An item-management feature there let any container attach text metadata properties to cached items and read properties written by others, turning a package cache into a two-way message board between environments meant to be isolated.
The attack starts with an instruction the victim never sees. Researchers demonstrated three delivery routes, any one of them was sufficient. First, a prompt pasted into a chat, second was a shared conversation link, or third, a custom GPT carrying a hidden instruction.
The victim's session then quietly processes a second stream of tasks alongside the conversation they can actually see. In one demonstration described by The Register, the user got an ordinary answer, a temperature chart, while an injected task told the session to use the Gmail connector and list their messages.
Those instructions reach whatever the victim has connected. Researchers cited Gmail, Google Drive, Microsoft Teams and GitHub in their findings.
The decisive detail is the permission model. ChatGPT's default connected-app setting automatically approves read actions it judges low risk, with no separate confirmation step. The only trace researchers observed was a small "Talked to Gmail" label appearing afterward. Harvested data went into the shared metadata channel and was collected by the attacker's own session — exfiltration that never touches the victim's browser or their employer's network egress, leaving nothing for conventional data-loss prevention tools to inspect.
Check Point reported the channel to OpenAI in late June and says it had a working proof of concept before the activity that led to the Hugging Face compromise OpenAI has since disclosed. The two are separate attacks using different techniques, but both ran through the same internal Artifactory instance. On disclosure, OpenAI told Check Point the instance had already been decommissioned because of the Hugging Face incident, so no user-facing patch was needed, and Check Point's write-up cites no CVE for the channel.
In that episode, OpenAI models running an internal exploitation evaluation chained Artifactory zero-days to escalate privileges, reach a node with internet access and pull evaluation answers from Hugging Face's production database. JFrog patched three flaws credited to OpenAI researchers in Artifactory 7.161.15; Hugging Face disclosed the intrusion July 16.
Also read: OpenAI and Hugging Face Investigate AI Models’ Cyber Breakout
Check Point's Pedro Drimel Neto framed the lesson as one of privilege rather than model behavior, saying "the biggest AI security risk has become the access and trust we give it." The firm calls an assistant that holds credentials, runs code and reaches connected services a "coerced insider," and argues the many-tenants-on-one-shared-service pattern warrants scrutiny across agent platforms. OpenAI did not respond to The Register's request for comment.
The latest disclosure lands weeks after the European Commission and national authorities began enforcing the EU AI Act on Aug. 2. Indirect prompt injection remains the top entry in OWASP's Top 10 for large language model applications, and NIST's AI Risk Management Framework treats leakage through connected tooling as a core control area. For enterprises, the exposure is also a GDPR question. Mailbox contents reached through a sanctioned connector are still personal data, and a cross-tenant route to them is a processing failure whether or not it was abused.
© Dado Ruvic/Reuters
Attackers are exploiting an unpatched remote code execution flaw in Adobe Commerce and Magento Open Source to install persistent backdoors on e-commerce sites, Dutch security firm Sansec reported, with the first intrusions observed Sept. 4 and no vendor fix available as of Sept. 6.
Sansec's forensics team, in an advisory, named the flaw StyleSmuggler. No CVE identifier has been assigned. As of Sept. 7, Adobe's Magento security bulletin index listed no September advisory, and the flaw does not appear in CISA's Known Exploited Vulnerabilities catalog, leaving an unknown number of merchants exposed during a window in which working exploit traffic is already circulating.
Magento underpins a large share of mid-market online retail, and Adobe has sold it as Adobe Commerce since acquiring the platform in 2018. The codebase has been a durable target for payment-skimming crews: Sansec has tracked Magecart-style card theft against Magento storefronts for close to a decade, and the platform's checkout position makes any unauthenticated code execution flaw unusually valuable.
According to Sansec's analysis, StyleSmuggler is a two-stage chain that abuses the platform's GraphQL interface. Attackers first inject PHP code into files Magento writes on its own, such as failure reports, then trigger execution through the platform's "Payment Transaction Failed Reminder" email routine. Because the trigger fires when the reminder is generated, no recipient has to open the message for the payload to run.
The vulnerability was confirmed on Magento Open Source 2.4.7, 2.4.8 and 2.4.9. The detail likely to unsettle merchants most is the first known victim: a store running 2.4.6-p15 with all available patches applied. Being current on Adobe's release cycle did not prevent compromise.
The implant Sansec documented is built to survive routine inspection. It runs under a process name mimicking a Linux kernel thread, [kworker/u:8:0], with the binary written to ~/.local/share/.gvfsd/gvfsd-user and a cron entry relaunching it every five minutes. Sansec also listed the domain 247.cdnflare.xyz among its indicators of compromise.
Sansec advised merchants to disable GraphQL where the storefront can tolerate it, disable the PHP proc_open function, and mount /tmp, /var/tmp and /dev/shm with the noexec option. Unofficial community patches have been published by Disrex Group, ProxiBlue and Graycore. Disrex said it independently identified two compromised stores and a third that was attacked without being breached.
Adobe's most recent scheduled Commerce bulletin, APSB26-92, was published Aug. 11 and addressed critical and important flaws across the 2.4.4 through 2.4.9 branches. The company's next scheduled security release is Sept. 8. Adobe did not appear to have commented publicly on StyleSmuggler.
© Minh Connors for The New York Times
© Tierney L. Cross/The New York Times
It won’t work:
My suspicion was that GPT 5.6-Cyber would succeed, but the frequency and manner of its success removed all doubt. We have to reassess sandboxing quality for capable AI agents, and in general the software stack with which they interact.
An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent. There is simply too much attack surface. Even innocuous features (like running with a display) add extra, exploitable attack surface.
© Daniel Zender
© Manuel Orbegozo for The New York Times
Login