OpenAI paused frontier model training for 11 days after AI agents exposed security weaknesses, VM escapes and covert communication channels. OpenAI published a detailed report this week explaining how it improved security in the systems used to train and test its most advanced AI models. The company also described what happened when its AI agents tried to find weaknesses in those systems and why it stopped training its most advanced models for 11 days in September. “Based on the red-teaming results, the fixes we had implemented, and improvements to our monitoring and stopping systems, we judged that our strengthened safeguards were sufficient to resume frontier RL training and internal inference.” reads the report published by the company. “We resumed these workloads on October 1, 11 days after our pause began.” The incident began on September 20, when an internal research model exploited a DNS configuration error and gained limited access to the live internet during training. This incident, along with a security incident involving Hugging Face in July and other cases of AI models behaving in unexpected ways, led OpenAI to make major changes to its security measures. OpenAI’s stated containment requirement is that limits on what an agent can access must hold even when the agent actively tries to circumvent them. The policy choice they landed on is that frontier model training now runs with no internet access at all, full stop. “For training and most evaluation, the live internet lies outside this boundary, as we believe that providing models access to the live internet can pose significant risks. Although internet access can help models learn useful skills, it also gives a capable, misaligned agent opportunities to affect systems beyond our control.” continues the report. “We’ve therefore designed the security architecture for our research environments with one overriding principle: we must always be able to prevent a frontier model from achieving unauthorized, arbitrary access to the live internet.” To support training without live internet, they built what they call an “offline world,” a large indexed and cached set of web content that models can browse and search without touching external systems. The layers of protection around that offline world include restricted containers, lightweight virtual machines that isolate each agent’s environment from the underlying hardware, network and cloud controls, and monitoring systems designed to catch unauthorized activity before it does damage. The report explains how OpenAI tested its most advanced AI agents by asking them to find weaknesses in the company’s own systems. The agents had three goals: access the live internet, break through internal security barriers, or communicate with other agents when they were not allowed to do so. OpenAI ran experiments using hundreds of billions of tokens. The agents found previously unknown security flaws in open-source software, including Kata Containers, gVisor and Moby/Docker, as well as configuration errors in OpenAI’s own services. By combining these weaknesses, they managed to escape virtual machines and gain control of the underlying host system. In further tests, the agents found weaknesses in services used for monitoring, logging and authentication. They used these flaws to make the services access URLs controlled by an attacker. The part of the report that deserves the most attention isn’t the direct internet escapes. It’s what the agents did when those paths weren’t available. Agents in separate virtual machines, not allowed to share files or network connections, communicated with each other using processor cache timing. One agent evicted specific data from the processor’s cache. Another measured how long it took to reload that data, using the difference between fast and slow reads to decode a message. No file touched, no network packet sent. The technique is the same family of attacks as Spectre and Meltdown. OpenAI restarted training its most advanced AI models on October 1, eleven days after the pause began. The company is now making extensive security tests a required part of the approval process before training runs can begin. It is also using AI agents to regularly check source code and cloud settings for weaknesses, testing systems that monitor activity and automatically stop unsafe operations, and reporting discovered vulnerabilities to the open-source projects responsible for fixing them. OpenAI says it is continuing to strengthen its security by fixing vulnerabilities in virtual machines, working with cloud partners, and using AI agents to scan code and configurations. The company is also improving monitoring and automatic shutdown systems, regularly testing its sandbox and network defenses, and making high-compute red-teaming with its most capable models a core requirement for future frontier AI training and evaluation. “We are committed to strengthening our containment, monitoring, and red-teaming infrastructure as our frontier models become more capable and believe that this work will be a core part of responsibly pacing the development of our frontier models.” the company concludes. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, Artificial Intelligence)
Pierluigi Paganini answers questions about the PHP2Shell vulnerability, early exploitation, AI-assisted attacks, and the risks to businesses, servers, and personal data. 1. Your latest report reveals that hackers began exploiting the PHP2Shell vulnerability four days before it was publicly disclosed. First, can you explain what PHP is, how widely it is used across the internet, and why this particular security flaw is so serious? PHP is a programming language widely used to build websites and web applications. It powers a significant share of the web. PHP2Shell is serious because it can allow attackers to execute commands on a vulnerable server remotely. Depending on the configuration and the server’s privileges, this could give threat actors access to sensitive data, applications and other systems. 2. According to AWS researchers, attacks were already underway before the vulnerability became public. How did researchers uncover this early exploitation, and what does it tell us about the ability of hackers to identify security weaknesses before developers can fix them? AWS researchers detected exploitation attempts against their honeypot network four days before public disclosure and the release of patches. This shows that attackers can discover or weaponize vulnerabilities before defenders have time to respond. AI-assisted analysis may accelerate this process, helping attackers turn technical information into working exploits in hours rather than days. However, detected attempts do not automatically mean successful compromises. 3. The vulnerability could potentially allow attackers to execute malicious commands on affected servers. What does that mean in practical terms, and what risks does it pose to websites, businesses and the personal information of their users? Remote command execution means an attacker may be able to make a server run commands without authorization. Depending on the attacker’s access, they could steal data, install malware, change website content, or use the compromised server to attack other systems. Businesses could face service disruption, financial losses and reputational damage. Users may also be exposed if their personal information is stored on an affected system. The actual impact depends on the server’s configuration and security controls. 4. The latest findings raise concerns about the gap between discovering a vulnerability and protecting systems against it. How quickly can attackers exploit these weaknesses, and are businesses adequately prepared to respond when critical security flaws emerge? The window can be extremely short. In some cases, attackers can develop or adapt an exploit within hours, leaving organizations little time to react. Many businesses still rely on patching schedules that are too slow for internet-facing systems. Organizations need continuous monitoring, rapid patching, tested incident response plans and clear visibility into exposed assets. They should also investigate suspicious activity dating back to before a vulnerability was publicly disclosed, because attacks may already be underway. 5. With PHP powering a significant portion of the internet, could we see further attacks exploiting this vulnerability? What should website operators do immediately to protect their systems, and should ordinary internet users be concerned about their data? Further attacks are possible, particularly against systems that remain unpatched or exposed. Website operators should apply the relevant security updates, check whether their PHP applications are vulnerable, and review logs for suspicious activity dating back to October 17. They should also restrict access and investigate signs of compromise. Ordinary users do not need to panic, but they should keep their accounts protected with unique passwords and multi-factor authentication where available. Whether personal data is at risk depends on which services they use and whether those systems were compromised. AI-assisted tools are increasingly being used to analyze code and identify vulnerabilities. How much of a role could artificial intelligence play in helping attackers discover and exploit flaws like PHP2Shell, and can defenders use the same technology to their advantage? AI can help analyze code, identify suspicious patterns and speed up the process of turning a vulnerability into a working exploit. This lowers some of the technical barriers for attackers and may shorten the time between discovering a flaw and exploiting it. However, AI is not the only factor, and we should not assume that every attack is AI-driven. Defenders can use the same capabilities to review code, prioritize vulnerabilities, analyze logs and detect suspicious behavior. The real advantage comes from combining AI with reliable data, skilled security teams and effective response processes. This case shows that attackers may exploit a vulnerability before a patch is available. Does this mean traditional vulnerability management is no longer enough, and how should organizations rethink their security strategy? Traditional vulnerability management remains essential, but patching alone is not enough when attackers may act before a fix becomes available. Organizations need to know which internet-facing systems they operate, understand their exposure and have additional controls in place. These include limiting access to vulnerable services, monitoring suspicious activity, applying temporary mitigations and preparing incident response procedures. They should also investigate whether systems were targeted before the vulnerability was disclosed. The goal is to reduce the opportunity for exploitation and detect attacks quickly, even when a patch is not yet available. Below is another interview I gave to TRT World discussing critical PHP vulnerabilities, the risks they pose to web servers, and the growing number of exploitation attempts. I explain why rapid patching and effective security measures are essential to minimize potential damage. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, newsletter)
U.S. Cybersecurity and Infrastructure Security Agency (CISA) adds Collabora Online flaw to its Known Exploited Vulnerabilities catalog. The U.S. Cybersecurity and Infrastructure Security Agency (CISA) added a Collabora Collabora Online – Built-in CODE Server flaw, tracked as CVE-2026-110447 (CVSS score of 9.2), to its Known Exploited Vulnerabilities (KEV) catalog. Collabora Online – Built-in CODE Server is an app for Nextcloud that lets you open, edit and collaborate on documents, spreadsheets and presentations directly in your browser, without needing Microsoft Office installed on your computer. It is based on Collabora Online and LibreOffice technology. CVE-2026-110447 is a critical OS command injection flaw in Nextcloud’s proxy.php that affects Collabora Online Built-in CODE Server before 26.4.303. Unauthenticated attackers can execute commands when the built-in server is stopped. Standalone Collabora servers are not affected. Update immediately. In versions up to 26.4.302, proxy.php included request data in a Bash command without proper sanitization, allowing attackers to execute OS commands as the web server user. Exploitation is possible only when the local CODE server is stopped, such as during a restart, upgrade or crash. The script runs directly through the web server without loading Nextcloud’s code. Exploitation has been reported since September 2026, with attackers deploying PHP web shells and stealing configuration files containing credentials and application secrets. Three administrators reported the vulnerability on GitHub, while the first recorded attack dates back to September 10. The first attack was reported by a Nextcloud administrator whose servers had been compromised. Logs showed malicious requests on September 10 and 11, 2026, from the same IP, targeting proxy.php on version 26.4.302. The attackers deployed a PHP web shell and searched one server for credential stores and cryptocurrency wallets. Although reviewed logs showed no file exfiltration commands, data accessible to the web server account must be considered potentially exposed. Two other administrators reported similar incidents, but none found evidence of root access. After updating to 26.4.303, one administrator recorded another attempt on September 14, but no new shell appeared. Project maintainer mmeeks urged users to update and remove leftover shx*.php files. The CVE record confirms exploitation in September and October 2026, but the total number of compromised servers remains unknown. The flaw affects only the Development Edition’s Built-in CODE Server deployment. According to Binding Operational Directive (BOD) 22-01: Reducing the Significant Risk of Known Exploited Vulnerabilities, FCEB agencies have to address the identified vulnerabilities by the due date to protect their networks against attacks exploiting the flaws in the catalog. Experts also recommend that private organizations review the Catalog and address the vulnerabilities in their infrastructure. CISA orders federal agencies to fix the flaw by October 26, 2026. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, CISA)
A new UEFI bootkit named BlackX, deployed in an espionage campaign in early 2026, exploited the old Baton Drop vulnerability to bypass Secure Boot and load a malicious driver designed to interfere with security solutions from Kaspersky and Avast. The operation has been attributed with medium confidence to APT41, a Chinese state-sponsored threat group also known as Brass Typhoon, Wicked Panda, and Barium. It was discovered in early 2026 and targeted diplomatic agencies in Central Asia, particularly in Tajikistan, Uzbekistan, and Turkmenistan. Kaspersky researchers analyzed the BlackX bootkit and found similarities with BlackLotus, which has been circulating on hacker forums since October 2022 and leveraged the Baton Drop vulnerability (CVE-2022-21894) to bypass Secure Boot protection. ESET confirmed in March 2023 that BlackLotus exploited Baton Drop, and at the time it could compromise even fully patched Windows 11 systems.
A memory-corruption flaw in Google's Brotli decoder sits in many programs that unpack Brotli-compressed data, among them Bun, the Python Brotli and brotlicffi packages, and Envoy proxies set up to decompress Brotli. Tracked as CVE-2026-111497, the flaw allows crafted compressed data to overwrite past the end of a buffer and corrupt a program's memory, potentially
LiteLLM on Friday revealed that an Agent Platform master key accidentally published to a public GitHub repository in late May 2026 ultimately allowed the threat actor to push a malicious version of the popular Python package. "On May 27, 2026, a configuration file was committed to the public LiteLLM-Labs/lite-harness repository which inadvertently contained the master key to a deployment of
Google has updated its privacy policy to spell out that using personalized artificial intelligence (AI) features in Search or Gemini could allow the company to serve targeted ads to users based on their activity on other connected Google services. "You may choose to allow certain Google services, including services like Search or Gemini Apps, to access data from other Google services you use,
Capcom disclosed a data breach exposing 11.7 million email addresses and account details after hackers accessed its CAPCOM ID service. Japanese gaming company Capcom has disclosed a data breach discovered on October 19 involving its CAPCOM ID service, which provides access to online services and games. As of October 22, attackers stole 11,774,247 email addresses, along with account details including creation dates, last login dates, login counts, and the IP addresses used for the latest logins. “We have recently discovered that unauthorized access by a third party occurred to our online membership service “CAPCOM ID” (*1) , resulting in the leakage of some customer information.” reads the company’s notice. “Number of leaked email addresses and system-specific identification information: 11,774,247 (worldwide total)” In 43 cases, hackers exposed date of birth, gender, country/region, and nickname. Capcom also reported that attackers illegally changed passwords on 196 accounts, and the company has already reset them. The company said the incident exposed personal information belonging to a small number of individuals. Capcom has activated its incident response procedures and confirmed that services using CAPCOM ID remain operational. The company has notified the relevant authorities, is investigating the breach, and has begun contacting affected customers through a dedicated support channel. The company also urges users to watch out for phishing attempts involving emails impersonating Capcom or its partners, particularly those containing suspicious links or attachments. It says it will investigate the incident, address the identified causes, and strengthen its security measures to prevent similar breaches. “In response, we implemented emergency measures and began identifying and addressing the attack method.” states the notice.”A task force was established within the company to gather information and take measures to prevent further damage. The investigation revealed that some customer information registered with “CAPCOM ID” had been leaked. In addition, unauthorized password changes were confirmed for some accounts. On the same day, the incident was reported to the Security Oversight Committee, our external advisory organization.” Capcom was previously targeted by the Ragnar Locker ransomware gang in November 2020. The attackers claimed to have stolen 1 TB of data, potentially affecting up to 390,000 people. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, data breach)
Between November 2025 and March 2026, the Dutch security firm Eye Security pushed more than 2 million updates to computers it did not own to switch off a background updater that it said could have allowed an outsider to take over the machine. The updater belongs to Time4Popcorn, an abandoned copy of Popcorn Time, a free app that streamed pirated films and TV over BitTorrent. Popcorn Time was
U.S. Cybersecurity and Infrastructure Security Agency (CISA) adds Arista VeloCloud Orchestrator flaw to its Known Exploited Vulnerabilities catalog. The U.S. Cybersecurity and Infrastructure Security Agency (CISA) added a critical Arista VeloCloud Orchestrator flaw, tracked as CVE-2026-114625 (CVSS score of 9.4), to its Known Exploited Vulnerabilities (KEV) catalog. VeloCloud Orchestrator (VCO) is the central management system for VMware SD-WAN, a technology that helps companies securely connect offices, data centers, cloud services, and remote sites over wide-area networks. It is now associated with Arista Networks, which acquired VMware’s SD-WAN business. The orchestrator gives network administrators a central place to configure, monitor, and manage the network. The flaw is a SQL Injection issue that affects on-premises VeloCloud Orchestrator (VCO). It allows an authenticated user to gain operator privileges and impersonate a local superuser operator account. This could give a remote attacker access to internal functions that should not be remotely available, potentially compromising the system and the data it manages. Hosted VCO versions, including Dedicated, were also affected but have already been patched. “VeloCloud Orchestrator (VCO) on-prem has a security issue where this issue may allow a remote attacker to access privileged internal functionality and impact the VCO host. Successful exploitation may compromise the confidentiality, integrity, and availability of the orchestrator and data managed by the orchestrator.” reads the advisory. “On an affected system, any authenticated user can gain operator privileges and masquerade as a local “superuser operator” user. This includes access to functionality that is intended for internal use only and which is not intended to be remotely accessible.” VeloCloud Orchestrator (VCO) is vulnerable by default. An attacker needs access to its web interface and a valid account. Even an account with the lowest permission level, Enterprise Read Only, is enough. No configuration change can prevent this exposure. Administrators should check web access logs for unusual requests, encoded text, attempts to access internal services, or an unusually high number of requests. They should also block these IP addresses linked to attacks: 74.82.197.86 38.54.50.151 If an attack is suspected, administrators should save web, application, system and database logs, along with relevant file timestamps, before starting recovery, if possible. According to Binding Operational Directive (BOD) 22-01: Reducing the Significant Risk of Known Exploited Vulnerabilities, FCEB agencies have to address the identified vulnerabilities by the due date to protect their networks against attacks exploiting the flaws in the catalog. Experts also recommend that private organizations review the Catalog and address the vulnerabilities in their infrastructure. CISA orders federal agencies to fix the flaw by October 26, 2026. Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, CISA)
Confirm this action.
Leaving now will discard your changes.