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)
Blockchain analysis firm Chainalysis has revealed that its ongoing investigation into the agentic cyber attack targeting its systems also exposed names, usernames, password hashes and live tokens for all users. "While we investigated, we removed access to Reactor and Data Solutions," the company said. "At this time we continue to have no evidence that any investigations data has been accessed
A backdoor has been found hiding in the web server that runs Control Web Panel (CWP), a free panel for managing Linux hosting servers, researchers at QiAnXin's XLab said this week. The backdoored web server executes commands that attackers send via web requests, and those requests never appear in its access logs. Installing it takes root access, so the attackers must already control the server.
Two flaws in Barracuda's Email Security Gateway, an email-filtering appliance, can be chained to run commands on it as root, its highest level of access, with no login required. The company released patches on Monday, and the security firm watchTowr detailed the attack chain on Thursday. One flaw, CVE-2026-116606, is an authorization bypass. An unauthenticated attacker can use it to restore a
The FBI and CISA warn that hackers are actively targeting industrial refrigeration and cold-chain monitoring systems worldwide, potentially causing food spoilage, equipment damage, and fire hazards. The warning was issued jointly with the U.S. Departments of Health and Human Services (HHS), Agriculture (USDA), and Transportation (DOT), urging critical infrastructure operators to secure vulnerable refrigeration controllers used in healthcare, food production, chemical facilities, and transportation. "Every organization that depends on refrigeration and monitoring systems should assume it could be a target," said Chris Butera, CISA's Acting Executive Assistant Director for Cybersecurity. According to a joint advisory published Thursday, attackers are exploiting weaknesses in unpatched or internet-accessible electronic temperature controllers and commercial refrigeration management systems.
OpenAI disclosed that its GPT-6 Astra frontier model sometimes hindered safety research by complicating simple tasks, abandoning viable approaches, and silently refusing researchers’ requests. During evaluation, the AI company's model reported nonexistent or self-made blockers without explaining its restrictions to users. OpenAI said it first received a report of what it calls "covert underperformance" in Astra on August 20. The company then conducted targeted evaluations to investigate the behavior and determine its causes, noting that it had not observed the same issue in GPT-5.6 Sol. OpenAI says it received the first report of what it calls “covert underperformance” in Astra on August 20. The company then ran specifically designed evaluation experiments to determine the extent and cause of this behavior, noting that the issues were not observed in GPT-5.6 Sol.
A newly disclosed flaw involving OpenSSH and musl, dubbed "*sshole," allows attackers to log in to certain Alpine Linux and other musl-based Linux accounts configured to block password authentication simply by entering an oversized password. The flaw only affects OpenSSH servers running on Linux distributions that use the musl C library, including Alpine Linux, OpenWrt, Buildroot, and Yocto, under certain authentication configurations. Security researcher Ozgun Kultekin, who discovered and released details on the vulnerability today, says the flaw has existed since 2016 and stems from how OpenSSH handles password verification errors on systems using the musl C library. Linux accounts can be configured to prevent password logins by replacing their password hash with an asterisk (*) in the /etc/shadow file. Because this is not a valid password hash, no password should allow access to those accounts.
A new Linux malware called CWPdoor is being distributed through a trojanized version of cwpsrv, the web server behind the Control Web Panel (CWP) management interface. CWPdoor acts as a passive backdoor that sits dormant on the compromised system until the attacker sends a specially crafted request. Researchers at XLab, the cybersecurity research arm of QiAnXin Technology Group, describe CWPdoor as "exceptionally stealthy" due to its passive triggering and log suppression feature. CWP, formerly known as CentOS Web Panel, is an open-source web hosting administration solution similar to cPanel and Plesk that allows users to manage web servers and services such as email, DNS, and databases. According to XLab, more than 340,000 CWP instances have been exposed on the public web over the past month.
Confirm this action.
Leaving now will discard your changes.