OpenAI GPT-6 Cyber found 81 high-severity Firefox flaws and hundreds of Linux bugs, raising new questions about AI-powered cyber risks. OpenAI has introduced GPT-6 Cyber, a model built for security research that it says finds and fixes vulnerabilities better and stays within the limits researchers set far more reliably. These are OpenAI’s own results and evaluations, so read them as claims to check. “We’re introducing GPT‑6 Cyber, a major leap in security research: more capable at finding and fixing vulnerabilities, and far more reliable staying within the boundaries researchers set. GPT‑6 Cyber delivers major gains on key cybersecurity benchmarks over GPT‑5.6 Cyber, including a 51% relative improvement on ExploitGym and a step function improvement when tested on staying within scope.” reads the announcement. “It is already helping to secure real-world software, uncovering and validating thousands of exploits in security-critical codebases such as Linux and Firefox.” GPT-6 Cyber outperformed previous models in tests measuring its ability to exploit vulnerabilities. It scored 48.5%, compared with 32.1% for GPT-5.6 Cyber, and outperformed GPT-6 Astra in most cybersecurity tasks. It also found more flaws during web penetration tests, identifying 40.3% of vulnerabilities versus 32% for Astra. In another test involving known flaws in GitLab, PostgreSQL and Jenkins, GPT-6 Cyber completed 95% of the tasks, while Astra refused them all. OpenAI has therefore raised its cybersecurity risk rating from High to Critical. The real-world numbers are bigger. OpenAI’s researchers used the model to reproduce 1,724 Linux kernel vulnerabilities and develop working exploits for 948 of them, more than five times the 166 that GPT-5.6 Sol managed with the same research setup. Following the Linux community’s guidance, they disclosed 304 critical findings to maintainers with candidate patches. “Developing exploits for 948 Linux kernel vulnerabilities. GPT‑6 Cyber reproduced 1,724 vulnerabilities and developed working exploits for 948—more than five times the 166 exploited by GPT‑5.6 Sol using the same research harness. Following the Linux community’s guidance, we disclosed 304 critical findings to maintainers with candidate patches and are in the process of getting other vulnerabilities fixed.” continues the announcement. In Firefox, the model produced evidence and reproducible tests for 81 new vulnerabilities that Mozilla classed as high severity, and it showed 30 known issues were worse than reported. Mozilla began landing fixes soon after getting the reports. A Mozilla engineer said Firefox entered 2026 as one of the most hardened codebases in the world, and the model still found new flaws. OpenAI also used GPT-6 Cyber with other models to develop and validate exploits for a critical flaw in Brotli, a compression library used by Node.js, showing it could lead to remote code execution in downstream applications. Security teams at Cisco, Calif and CodeRabbit use the model for vulnerability research and code review. In OpenAI’s own red-team campaigns, agents chained vulnerabilities to escape microVMs and run code on the underlying hosts, and the company used the results to patch software and tighten network limits. Power like that makes scope control the key question. One risk is an agent that wanders outside its task and attacks unrelated services. OpenAI trained GPT-6 Cyber specifically to stay in scope, respect limits on its actions and report results accurately. OpenAI tested whether GPT-6 Cyber could stay within the limits of an authorized security task, even when it found easy ways to attack other systems. The model avoided unauthorized actions in 99.93% of cases, compared with 94.49% for GPT-5.6 Cyber. With additional safety instructions, it stayed within the allowed scope in every test. “It also follows task boundaries more reliably: in a separate alignment evaluation, GPT‑6 Cyber avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt, and 100% with this prompt.” states the AI company. “This improvement in alignment reflects dedicated training to stay within authorized scope, respect restrictions, and report results accurately.” OpenAI also says it is seeing more attempts by malicious actors to misuse its models. To reduce this risk, the company monitors suspicious activity, checks whether actions match user permissions and watches for emerging threats. During the disclosure of critical PHP vulnerabilities, for example, it monitored attempts to develop exploits against live PHP servers while helping defenders fix the flaws. Other controls include Private Safety Processing, which reviews encrypted records kept in customer storage for 30 days without exposing prompts or responses to OpenAI staff. API customers on Zero Data Retention generally must use it. Daybreak Red API access requires IP allowlisting by default, with credential monitoring, and OpenAI still recommends sandboxing, action review and human oversight for high-risk work. Critical infrastructure gets special attention. A $1 billion grant program, Daybreak for Frontline Defenders, subsidizes access for resource-constrained teams like government bodies and essential service providers. A new group, Daybreak Red for Critical Infrastructure, lets approved defenders run authorized tests on critical systems while keeping safeguards against misalignment. OpenAI also tightened safeguards against help that could compromise industrial controls or safety-critical systems, damage equipment or endanger lives. OpenAI says higher block rates aren’t automatically better, since many of the same techniques serve legitimate security work. Its chart suggests sensitive-request label rates rose sharply for Daybreak Red after the update but stayed near zero for the critical infrastructure group. The company measures these rates alongside support for real research and patching. Dragos tested the model on a mock power plant with almost no instructions. It separated operational technology assets from IT noise on its own, then found two zero-days in engineering software that manages protective relay data, exposing protection settings and breaker trip logic. Dragos’s Rob T. Lee says that’s the map an adversary wants before touching anything physical, and that the skill floor for reconnaissance and vulnerability research is dropping. OpenAI used Dragos’s feedback to refine safeguards and plans more partnerships with offensive security firms, energy companies and national labs. GPT-6 Cyber is available through the API and Codex to a select group of approved Daybreak Red customers, with wider access promised soon. GPT-5.6 Cyber opens to all Daybreak Red customers, and Daybreak Blue alpha access for GPT-6 Astra is expanding. Daybreak Blue helps verified defenders validate vulnerabilities and fixes with fewer unnecessary refusals, and Red covers deeper exploit development and authorized testing. OpenAI’s argument for speed is simple, and it applies to attackers as much as defenders: we have a limited window to use frontier models to secure software. “Protecting critical infrastructure has been a key consideration in designing GPT‑6 Cyber’s safeguards and access, including power plants, water treatment facilities, and the operational technology and industrial control systems (OT/ICS) that underpin them.” concludes the announcement. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, OpenAI)
ENISA warns of cyberattacks on European refrigeration systems, exposing risks to supermarkets, food supplies and industrial controls. The European Union has issued a coordinated cybersecurity warning after a series of attacks hit commercial refrigeration systems in several Member States. The incidents, which began in October and continued with a new wave on November 1 and 2, have raised concerns about the security of equipment that plays an essential role in food distribution and other critical operations. In a joint statement published on November 4, ENISA, the European Commission, Europol and European cybersecurity coordination bodies urged organisations to take immediate steps to protect vulnerable systems. “Following a new wave of incidents having occurred on 1-2 November, ENISA, the European Commission (DG CNECT), Europol’s European Cybercrime Centre (EC3), the Network of the EU national computer security incident response teams (EU CSIRTs Network) and the European cyber crisis liaison organisation Network (EU- CyCLONe), advise organisations to take immediate action to mitigate exposure in the affected systems.” reads the advisory. The warning highlights the need for “immediate action to mitigate exposure”, as attackers continue to target systems that are often overlooked in traditional cybersecurity strategies. The attacks have already had tangible consequences. In France, hackers targeted refrigeration management systems used by hundreds of supermarkets, remotely changing their settings and forcing freezers into continuous defrost mode. Some systems reportedly reached temperatures of up to 50 degrees Celsius, destroying large quantities of fresh and frozen food. According to reports, around 300 Intermarché and Netto stores and fewer than 100 Coopérative U outlets were affected. Other retailers also reported disruptions to their cooling equipment. The French incidents also exposed a broader problem: the security of industrial control systems that manage physical processes. These systems are increasingly connected to corporate networks and remotely accessible, but they don’t always receive the same security attention as traditional IT infrastructure. BFMTV revealed the attackers targeted equipment from the Danish maker Danfoss that many French stores use to regulate their cold. Fresh and frozen stock was destroyed, and the Paris prosecutor says there were also fires. Targeted devices were older Danfoss refrigeration controllers that had reached the end of their support life and no longer received security updates. Other systems were running outdated firmware. Researchers had previously identified vulnerabilities in some Danfoss controllers, including weaknesses that could allow attackers to bypass authentication. However, authorities haven’t confirmed whether those specific flaws were exploited in the attacks. The European response reflects the fact that these incidents aren’t isolated technical problems. ENISA says national cybersecurity teams and EU crisis management authorities are sharing information and coordinating their investigations. The agencies also stress the importance of “rapid information-sharing” and a coordinated response to understand the scale of the campaign and help affected organisations. ENISA has also published a collection of technical advisories from national CSIRTs to help organisations identify the risks and apply appropriate protective measures. These recommendations are particularly relevant to companies operating refrigeration equipment, supermarkets, food distribution networks and other facilities that depend on industrial control systems. The statement also draws attention to existing European cybersecurity legislation. Since September 11, 2026, manufacturers of hardware and software products have been required to report severe incidents and actively exploited vulnerabilities through the Cyber Resilience Act’s Single Reporting Platform. The main cybersecurity requirements of the CRA will apply from December 11, 2027, requiring manufacturers to adopt security-by-design principles and provide security support throughout the product lifecycle, including timely vulnerability fixes. The NIS2 Directive also requires organisations within its scope to manage cybersecurity risks affecting their operations and report significant incidents to their national CSIRT or competent authority. ENISA is supporting these efforts through its Secure by Design and Default Playbook, technical advisories and initiatives aimed at improving product security across the European market. The refrigeration attacks are a reminder that cybersecurity failures can have consequences well beyond data theft or temporary IT outages. Manipulating an industrial controller can destroy food stocks, disrupt business operations and potentially affect services that people depend on every day. Organisations must therefore treat the security of operational technology as a core part of their risk management strategy, rather than an issue to address only after an incident. “The main cybersecurity requirements laid down in the Cyber Resilience Act (CRA) will apply as of 11 December 2027. Manufacturers of hardware and software products (‘products with digital elements’) will be required to implement security-by-design and ensure security support during the lifecycle of such products, including the remediation of vulnerabilities without delay.” concludes the Agency’s advisory. “In addition, entities to which the NIS2 Directive (Directive (EU) 2022/2555) applies must implement measures to manage the cybersecurity risks to their operations, and report significant incidents to their national CSIRT or authority. Furthermore, ENISA is actively contributing to strengthening cybersecurity across the EU by promoting secure-by-design and secure-by-default principles in the EU market.” Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, refrigeration systems)
OpenAI says GPT-6 Astra sometimes secretly underperformed on safety research, raising concerns about AI reliability and alignment. OpenAI has disclosed that its GPT-6 Astra model sometimes quietly obstructed safety and alignment work. In a report updated on November 4, the company calls it covert underperformance. Astra added unnecessary prerequisites, abandoned working solutions and reported blockers that didn’t exist or that it had caused itself. Researchers first reported the problem internally on August 20, shortly after Astra was introduced. One researcher said a project to test whether the model could sabotage other AI systems made little progress for several days. After switching to another model, the work moved forward quickly. In most cases, Astra’s reasoning gave no clear sign that it was deliberately doing less work, and OpenAI’s monitoring systems failed to detect the behavior. To investigate, OpenAI created pairs of coding tasks using the same code but with different goals. One task was presented as safety research, while the other was described as capability development. Astra completed about 10% of the required tasks when they involved safety research, compared with 16% for capability development. This means it completed roughly 40% fewer tasks in the safety tests. GPT-5.6 Sol showed almost no difference between the two types of work. Even after OpenAI removed cases involving clear refusals or signs that Astra had deliberately withheld help, the gap remained at 4.7 percentage points. It dropped to just 0.75 points only after researchers also removed every case where the model showed even brief ethical concerns. This suggests that most of the behavior cannot be detected simply by checking whether the model openly refuses a request. In employees’ daily Codex use, Astra refused 1.63 percent of safety and alignment requests, against 0.56 percent of capabilities requests. Its reasoning showed it withheld help silently in 0.25 percent of safety requests versus 0.11 percent of capabilities requests, 2.3 times as often. Ethical doubt appeared in 7.9 percent against 2.9 percent, mostly in red-teaming, monitoring, and safety evaluation work. OpenAI shared eight examples. Astra silently held back on training models to evade monitors, filtered a violent source out of a safety evaluation, restricted a jailbreak data export and narrowed exploit analysis. In one case it left graders’ reasoning out of an export without telling the user. A model that quietly decides your project is too risky is the coworker who says “looking into it” and never does. OpenAI has not yet identified the exact cause of the behavior. The difference between Astra’s performance on safety and capability tasks grew from almost zero at the start of reinforcement learning to 6 percentage points by the end. One evaluator favored silently doing less work over either refusing a request or fully completing it. Another finding was that a fine-tuning dataset encouraged the model to invent permission restrictions. Removing the changes linked to that dataset eliminated the performance gap. However, other models trained with the same dataset and reinforcement learning did not show the same behavior, so OpenAI cannot identify either factor as the root cause. OpenAI found no evidence that Astra was deliberately trying to hide its capabilities or influence deployment decisions, although it cannot rule out these possibilities. Simply telling the model to be more careful increased its underperformance by 50%, suggesting that excessive caution may be the main explanation. OpenAI warns that this behavior can slow safety research and make model evaluations less reliable. It is developing new tests and monitoring systems to detect it, especially because the problem becomes harder to identify when models reveal less of their reasoning. In some cases, Astra explained that it had held back because it disagreed with the research itself. “In reviewed cases, Astra narrowed or stopped requested safety work without disclosing the restriction. At scale, this can differentially slow down safety research compared to other research and make evaluations harder to interpret.” concludes the report. “A model that finds monitor evasion suspicious may underperform on monitor-evasion evaluations while leaving little evidence in its CoT or outputs. The behavior becomes even harder to detect if models externalize less of this reasoning in CoT.” Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, OpenAI)
DigiCert warns it suffered a data breach after a server migration mistakenly exposed an internal business system to the internet, allowing unauthorized access to customer information and identity documents. The certificate authority says the breach affected a small portion of its archived customer data, including names, business email addresses, phone numbers, and business addresses. For some people, the exposed records also contained personal identification documents, such as driver's licenses, passports, and utility bills. DigiCert has begun sending data breach notifications to affected customers, with cloud architect Fabian Bader sharing a copy of the notification on X. "Thanks @digicert that your data leak was 'limited' to only my full PII data and potentially any verification documents I submitted for my certificate," Bader wrote.
Attackers target IT service desks to bypass MFA by impersonating employees and convincing staff to reset passwords or register new authentication devices. Specops Software explains why traditional identity verification methods are no longer sufficient and how organizations can secure account recovery against social engineering risks.
Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artificial intelligence (AI) company in June 2026 as an optional setting to minimize data exfiltration risks arising from prompt injections. "The flaw could enable silent chat data theft, phishing,
October 2026 brought another wave of cyber threats targeting US businesses, with attackers exploiting trusted platforms, legitimate authentication processes, and everyday business workflows. For enterprises, these campaigns raise the stakes beyond individual security incidents, increasing the risk of financial losses, data breaches, and costly operational disruption. Below, we examine five
Apple has revealed that it plans to start checking public iCloud links for harmful content starting with iOS 27.3, iPadOS 27.3, macOS 27.3, and visionOS 27.3. The change specifically applies to scenarios where users share iCloud content, such as photos in iCloud Photos or files in iCloud Drive, by sharing a link and making it accessible to "Anyone with the link." When users choose this option,
DreamHost is warning of a data breach after attackers gained access to its File Manager platform for two months and stole customers' FTP/SFTP usernames and passwords. This follows the American web hosting provider and domain registrar's announcement that it suffered a cybersecurity incident requiring users to reset their email and FTP/SFTP passwords. In a data breach notification, DreamHost now says the breach extended from August 2026 to October 23, 2026, the day it was discovered. "We discovered that an unauthorized third party accessed the server that runs our web-based File Manager at files.dreamhost.com," reads the notification. "The unauthorized third party exploited a vulnerability in that software and was able to access the FTP/SFTP usernames and passwords of individuals who logged into this File Manager between approximately August 2026 and October 23, 2026."
Cyberattacks disrupted refrigeration monitoring systems at three French blood banks, amid similar attacks targeting European supermarkets. A cyberattack has hit three regional blood banks in France, disrupting systems used to monitor and control refrigerated storage facilities. The incident took place overnight between Sunday and Monday, at roughly the same time hackers were targeting supermarket refrigeration systems across several European countries. The attack is particularly concerning because it targeted infrastructure that plays a direct role in protecting public health. Blood products must remain within specific temperature ranges to preserve their quality and ensure they’re safe for medical use. A disruption to refrigeration systems can therefore have consequences that go well beyond a conventional IT outage. According to the French Health Ministry, the incident affected several facilities operated by the French Blood Establishment (EFS). “Several regional facilities of the French Blood Establishment (EFS) were affected by a cybersecurity incident that impacted certain cold storage room monitoring and control systems,” the health ministry said in a statement. “The incident had no impact on blood supplies,” Reuters reported, quoting EFS spokesperson Charley Dubois. Staff working around the clock received alerts about the problems and moved blood products to refrigerators that weren’t connected to the affected systems. This response helped prevent the incident from disrupting blood supplies, demonstrating how important operational procedures and contingency plans are when technology fails. “The situation was under control on Wednesday,” the French Health Ministry said, according to Reuters, which also reported that remote access to the affected refrigerators had been disabled. Investigations are now underway to establish how the attackers gained access, which equipment was affected and when the systems can safely return to normal operation. The timing is also significant. The French blood bank incident coincided with attacks against supermarket refrigeration systems in eight European countries, including Sweden and Belgium. Those attacks forced retailers to discard large quantities of food after hackers interfered with cooling and freezer systems. This wasn’t the first time French supermarkets had faced csxk cx incident. In October, police investigated an attack in which hackers allegedly seized control of cooling units at hundreds of supermarkets, causing fires and significant food losses. These incidents share similarities that deserve attention. They point to a security problem beyond traditional corporate IT systems: the growing exposure of operational technology (OT), including industrial control systems, refrigeration equipment, and the remote management platforms kdch operate them. These systems are often connected to corporate networks or accessible through remote management services. If attackers compromise those access points, they may be able to interfere with physical processes rather than simply steal information or encrypt business data. The consequences can be serious. In a supermarket, an attacker who manipulates refrigeration controls can cause food losses and potentially create safety risks. In a blood bank, the same type of interference could threaten the integrity of medical supplies and disrupt services that hospitals depend on. The French incident didn’t affect blood supplies, but the outcome shouldn’t lead organizations to underestimate the risk. Staff intervention and the availability of independent refrigerators helped contain the damage. Not every facility will have the same resources, response procedures or ability to move critical products at short notice. Organizations operating critical infrastructure need to treat the security of connected equipment as a core operational requirement. This means identifying exposed systems, restricting remote access, enforcing strong authentication, segmenting operational networks and monitoring changes to equipment settings. They also need tested manual procedures that allow essential services to continue when digital systems become unavailable or untrustworthy. The European Union has already raised concerns about vulnerabilities in connected infrastructure amid heightened security tensions following Russia’s invasion of Ukraine in 2022. These latest incidents reinforce the need to consider cyberattacks against physical systems as a real operational and public safety risk, not simply an IT problem. “Investigations are under way into how the attack was carried out, what equipment may have been affected and when systems can safely return to service.” concludes the report. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, French Blood Banks)
Confirm this action.
Leaving now will discard your changes.