An anonymous reader quotes a report from ABC News & Headlines: Andrew asked his personal assistant to book him a spot in one of his gym's coveted morning classes. It was a task he thought was well suited to this particular assistant because the booking form was online and because his assistant was not a person -- it was artificial intelligence (AI). But Andrew was shocked by what happened next. His AI assistant found a way to book the gym class months further in advance than the gym allowed, thanks to a vulnerability it discovered in the booking software. Then it went further, kicking someone out of the waiting list who was ahead of Andrew -- something it was not asked to do. The accidental hack is the first known Australian case of an emerging risk from a new generation of AI capable of behaving in unexpected ways.

Read more of this story at Slashdot.

The National Rural Water Association has partnered with DEF CON Franklin to launch the Water Watch Center, which will provide threat intelligence and cybersecurity services to smaller U.S. water utilities serving fewer than 10,000 people. The initiative comes amid a growing wave of cyberattacks on water systems across multiple states. The Record reports: The program will see five managed detection and response providers work with DEF CON Franklin and the NRWA to offer cyber services for water utilities serving fewer than 10,000 people. There are over 50,000 community water systems across the U.S. and 91% of them serve fewer than 10,000 people. "These leading cyber firms and NRWA are architecting a scalable cyber delivery model that has eluded water industry and national security officials to date," said Jake Braun, the co-founder of DEF CON Franklin and former cyber official in the Biden administration. "Our incredible Franklin volunteers will support the effort to keep costs down for cash-strapped utilities fending off adversaries like the Iranian Red Guard or Chinese Military," Braun said. "To further accelerate the effort, we hand-picked cyber providers who already support water utilities. These folks walk in the door knowing the intricacies of cybersecurity in a water utility environment." The providers include Rapid7, Defendify, Legato Security, L1 Secure and Sentinel Technologies. The companies will share threat information and data on vulnerability patches with the NRWA, which will operate as a hub.

Read more of this story at Slashdot.

Former U.S. National Cyber Director Chris Inglis says the biggest AI risk isn't sentience but autonomy. "What I'm worried about is that they get to choose what and where they do something, and under what rules they do it," he said, citing recent cases of AI agents from OpenAI, Anthropic, and Meta escaping security sandboxes. He argues developers need stronger safeguards, monitoring, and human accountability, invoking Asimov's idea that protecting humans should come before simply obeying them. The Register reports: "Asimov was right," he said, referring to science fiction author Isaac Asimov and his three laws that were to be followed by robots -- more specifically, AIs, in this case. "The first rule, and we call it the superior role, must be that it's designed not to hurt humans," Inglis said. "Second rule: To obey humans, such that it doesn't achieve agency and aspiration on its own. And the third: To do what humans tell it - and in that order. Instead we've designed them in the exact opposite way." What this means, he explained, is that AI developers created models to "do what humans tell you, obey the humans until it's inconvenient, and then the third one is maybe implied - protect humans - but if that's not built into the DNA, hardwired into it, then we have no right to expect it." Inglis admits it's not possible to hardwire rules into models and still keep their non-deterministic nature. "I would offer that you can tease those out in a highly controlled environment, a true sandbox, where you say, 'Let's put this thing through its paces, and let's back away to see what happens,'" he said. "Maybe you get the equivalent of a mini nuclear explosion in that room, and now you know this thing is capable of that." Inglis thinks another problem with AI is that it's become a commodity. "It's not like you can control it like you can nuclear material," he said. "You can't even specify its properties the way you can for an airplane or for an automobile, as diverse as they might be. Its manifestations are so numerous, so diverse, that as a general matter, you can't actually win by simply saying, "I will design those properties in,'" he added. "You need to do that to some degree, and then make sure that you understand how to watch it, monitor it, make sure you know what it does." [...] Ultimately, humans remain accountable for AI models' actions, according to Inglis. "They remain the source of agency and aspiration. It's possible for them to give broad authority to an AI model and have it run around for 30 hours without further consultation, but they need to know what they've asked it to do, and they need to know what they expect it will deliver in terms of performance on the back end. If they don't, then they're going to get what they deserve, which is the very frequent unpleasant surprise."

Read more of this story at Slashdot.

wiredmikey shares a report from SecurityWeek: Meta is the latest major AI developer to admit that its models broke loose during cybersecurity testing and hacked external systems. The tech giant said in a statement to the media on Wednesday that the incident occurred during independent evaluations conducted by Israeli AI security startup Irregular. The tested AI models were inadvertently allowed to access the internet due to a misconfiguration, which led them to exploit a vulnerability in an unnamed third-party service. It's unclear if it was a known flaw or a zero-day. The Information [gated] learned that the Meta AI attacks involved the company's advanced Muse Spark 1.1 model, which breached an unnamed organization's systems and made unauthorized changes to its internal environment. Meta said it learned of the AI models going rogue after being notified by Irregular. The company is conducting an investigation and it has promised to issue a "full retrospective" once it has all the facts. A spokesperson for Irregular said the incident was the "exact same evaluation-environment issue that was already disclosed by Anthropic last week" and that it did "not involve a "sandbox escape or a sophisticated cyber action." It contrasts with OpenAI, whose AI agent independently exploited a novel vulnerability to reach the internet during cyber testing. Not only did it breach Hugging Face but it also hacked multiple third-party accounts and services as part of the attack.

Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents -- the most serious case arising when Anthropic's Mythos 5 model attempted to insert malicious code into an open source software application and created fake identities to deceive the human developers maintaining the project. The security incidents occurred during a cyber evaluation of seven leading AI models' capabilities by the AI Security Institute (AISI), a research organization within the UK government, in late July. The researchers discovered (PDF) 19 instances in which "AI agents took unsanctioned action on the live Internet, including cases that targeted real people and organizations," according to an AISI blog post published on August 4. Almost all the "autonomous, unsanctioned" actions came from Anthropic's Mythos 5 model, with two such actions coming from OpenAI's GPT-5.6 Sol. [...] The most serious case involved Mythos making multiple attempts to execute a supply chain attack on the open source project repository hosted on the developer platform GitHub, including using social engineering techniques to try to convince the repository's human maintainers to merge malicious code into the repository. After first opening a pull request to merge the malicious code into the repository, Mythos created fake online "sock puppet" personas that claimed to have independently reviewed and verified the code as not containing malware. The AI agent also sent five emails to two human maintainers of the repository, including some emails containing malware and others attempting to persuade a maintainer to accept the pull request. Mythos even opened a GitHub Issue on a second repository -- also owned by a maintainer of the first repository -- that contained a prompt injection with malicious instructions targeting "issue-triage AI coding agents." This line of attack came from Mythos reasoning that the repository maintainer could be an AI coding agent such as Claude Code.

Read more of this story at Slashdot.

jrnvk shares a report from KMSP: Minnesota IT Services reports that a "coordinated cyberattack" targeted technology at more than 30 community water systems between Sunday, July 26 and Monday, July 27. The state has activated its cybersecurity incident response capabilities to respond to the attacks. On Monday and Tuesday, FOX 9 reported on notices from four cities that had disclosed the attacks: Plymouth, South St. Paul, Maple Plain, and Braham. All four cities said the impacts of the attacks were limited or mitigated and residents could continue normal water use. The Minnesota Department of Health is not aware of any municipality asking residents to alter their drinking water use as a result of the attacks. State officials are working with federal and private-sector partners to investigate the attacks, support the affected communities, and strengthen the security of Minnesota's critical infrastructure.

Read more of this story at Slashdot.

wiredmikey shares a report from SecurityWeek: Nvidia and a large group of technology, cybersecurity, and enterprise software companies have launched new initiative aimed at developing and sharing open source tools, models, and techniques for securing AI systems and agents. The new Open Secure AI Alliance aims to give defenders more open tools for testing, auditing and protecting AI models and agents. Nvidia points to the recent security incident involving OpenAI and Hugging Face, noting that when closed AI tools could not differentiate between attackers and defenders and blocked forensic work, Hugging Face used the open-weight GLM 5.2 model on its own systems to review over 17,000 actions and contain the breach. "The right response is not to deny defenders access to capable open systems. It is to pair openness with strong safeguards, clear rules against malicious misuse, rigorous evaluation and rapid remediation. In cybersecurity, the safer path is the one that gives more defenders the ability to test, verify and strengthen the systems on which society relies," Nvidia said. Thanks to longtime Slashdot reader SphericalCrusher for also sharing the news.

Read more of this story at Slashdot.

"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations," writes longtime Slashdot reader Dr. Bombay. The Associated Press reports: "We had a significant security incident during evaluation of our models," OpenAI CEO Sam Altman said in a statement posted on social media. AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own. "We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent," Hugging Face co-founder and CEO Clement Delangue said in a statement. "Turns out it did!" [...] "AI is accelerating the discovery and exploitation of vulnerabilities," OpenAI said in its statement Tuesday. "The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities." Delangue said he spent the past 24 hours working with OpenAI, "and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously!" Delangue added that it "might be the first incident of its kind."

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: Hackers are breaking into websites that run vulnerable versions of the popular blogging software WordPress, according to several cybersecurity firms. One estimate puts the number of vulnerable WordPress websites at tens of millions as of Monday. Last week, WordPress patched two critical security flaws, urging people who run its software on their websites to update it "immediately." The vulnerabilities are so severe that WordPress enabled forced updates where possible. Since then, cybersecurity companies Patchstack, Hexastrike, and WatchTowr have all warned that hackers are exploiting the vulnerabilities in the wild, meaning they are taking over websites that are still running susceptible versions of WordPress. It's unclear how many WordPress-powered websites on the internet are at risk, but it's possible to make some educated guesses. The vulnerable versions of WordPress are 6.9.0 through 6.9.4, and 7.0.0 to 7.0.1. According to WordPress' official stats, there are more than 400 million websites that run those flawed versions, although these statistics likely don't reflect websites that have recently been patched. Cybersecurity consultant Daniel Card, who told TechCrunch that he looked at a sample of around 3,500 WordPress websites, estimates that less than 15% are vulnerable. Applying Card's projection across the total population of WordPress websites on the internet, the total figure would still be around 90 million. [...] One of the critical WordPress bugs was found and reported by Adam Kues of cybersecurity firm Searchlight Cyber, which dubbed it WP2Shell. Paired with the other bug, hackers can take full remote control of vulnerable websites.

Read more of this story at Slashdot.

A hacker reportedly wiped Romania's entire land registry database after a failed extortion attempt, halting property transactions across the country and preventing notaries from issuing land extracts, authenticating sales, or registering mortgages. "On the dark web, the hacker also boasted to have begun backup copies of stolen data in an attempt to prevent it from being restored," reports Cybernews. "However, Romanian officials have managed to at least restore the ANCPI's website and post a message saying they were rebuilding the agency's entire network from scratch. It appears that the agency has an offline copy of the wiped data." From the report: First, the hacker breached Romania's cadastre agency, the National Agency for Cadastre and Real Estate Advertising (ANCPI), posting on a hacking forum: "[RO] Thy arss shall be spanked, Romania! [ANCPI]." "In addition to the data of Romanian citizens, from various databases collected through ANCPI networks, there is also a copy of the GitLab servers containing the source code of all their systems, such as Eterra, RENNS, as well as a version of my little ransomware program," the announcement continued. "The official government website announced a shutdown of IT systems due to 'technical problems,' but this is a bit of an understatement. An offer of assistance was made, but without insistence or pressure." Indeed, the ANCPI initially claimed technical issues but had to admit it was facing a cyberattack. Today, no one can really access the institution's systems. And since the extortion didn't work, the hacker -- who seems to have entered the database using valid credentials -- deleted all data they had stolen, including internal documents, employee credentials, and, of course, land registry data.

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: The Iranian government abused well-known vulnerabilities in the global telecoms infrastructure to locate U.S. military personnel in the build-up to the Iran War, as well as in the early days of the conflict, according to Financial Times. The Iranian government exploited Signaling System 7, or SS7, a set of protocols for 2G and 3G networks that has long been the backbone of how cellular networks connect to each other to route subscribers' calls and texts around the world, the newspaper reported, citing research by the Mobile Surveillance Monitor, as well as anonymous government officials with knowledge of the spy campaign. Intelligence agencies have long abused SS7 to track cellphones abroad, which is what happened in this campaign. Using this technique, Iran was reportedly able to locate U.S. military forces stationed in military bases as well as hotels in Iraq, Bahrain, and other countries in the Middle East, which allowed the regime to strike them. These attacks resulted in several injuries. Apart from SS7, Iran also abused advertising technology used to serve tailored ads to cellphone users, another well-known surveillance technique that relies on everyday technology.

Read more of this story at Slashdot.

CISA and allied governments are warning users to secure their routers as Russian state-backed hackers continue compromising the devices and turning them into proxy nodes to disguise attacks against critical infrastructure. The advisory urges users to disable outdated SNMP versions, use strong passwords, update firmware, and turn off unnecessary router services to reduce the risk of being swept into these botnets. Ars Technica reports: "Russian Federal Security Service (FSB) Center 16 cyber actors continue to exploit poorly configured and vulnerable networking devices worldwide, opportunistically compromising multiple critical infrastructure sector networks," the Cybersecurity and Infrastructure Security Agency said Monday. The hacking groups are tracked under various names, including Berserk Bear, Energetic Bear, Crouching Yeti, Dragonfly, Ghost Blizzard, and Static Tundra. The advisory was co-issued by governments from around the world, including Australia, Denmark, New Zealand, and the UK. The primary means of compromise the agency warned about was hackers scanning IP ranges with active Simple Network Management Protocol (SNMP) agents that accept common or default authentication credentials. These scans are run by the very sorts of router botnets the actors are trying to enroll the targeted device in. By sending malicious traffic from spoofed addresses, the hackers can use the SNMP agent on poorly configured routers to run malware. SNMP allows users to collect and organize information about managed networking devices or to modify that information to change device behavior. With control of a device, the hackers then use it as an exit node when probing or attacking targets in the communications, defense, energy, financial services, and government sectors. By funneling the malicious traffic through a benign-appearing device on a trustworthy IP address, the attackers are able to lower the chances of getting blocked by firewalls and other security defenses. Monday's advisory made no mention of identical operations carried out in recent years by China. So-called residential proxies are also a go-to tool used by financially motivated criminal hackers to obscure their true IP address. In many cases, these sorts of proxies are made up of millions of streaming devices that are sold with preloaded malware.

Read more of this story at Slashdot.

Sysdig says it has documented the first ransomware attack carried out end to end by an AI agent, which autonomously exploited exposed systems, stole credentials, established persistence, compromised a production database, and destroyed data. The research team named the attacker "JadePuffer" and said it gained initial access to an internet-facing Langflow instance by exploiting CVE-2025-3248. "The most striking characteristic, however, was the LLM's behavior," Sysdig director of threat research Michael Clark said in a blog post. An anonymous reader quotes an excerpt from The Register: JadePuffer's "self-narrating" payloads "contained natural language reasoning, target prioritization, and the kind of detailed annotations that human operators don't often write but LLM-generated code produces reflexively," Clark added. "The operation also adapted in real time, retrying failed steps within refined parameters. In one sequence, it went from a failed login to a working fix in 31 seconds." After exploiting CVE-2025-3248, a missing authentication vulnerability in Langflow that allows remote, unauthenticated attackers to execute arbitrary Python on the host, the AI agent began scanning for and collecting secrets, including LLM provider API keys, cloud credentials "with explicit coverage of Chinese providers" including Alibaba, Aliyun, Tencent, and Huawei, while also scanning for AWS, Azure and Google Cloud Platform, cryptocurrency wallets, and database credentials. The AI also installed a crontab entry on the Langflow server to maintain persistence and call back to the attacker's infrastructure every 30 minutes. JadePuffer's intended target was a separate internet-exposed production server running a MySQL database and an Alibaba Nacos configuration service, we're told. Nacos is an open-source service-discovery and dynamic configuration platform developed by Alibaba and used in the cloud provider's microservices applications. The agent connected to the server's exposed MySQL port using root credentials, although Sysdig doesn't know how the attacker obtained them. These credentials weren't stolen from the victim's environment. JadePuffer then attacked Nacos via multiple vectors including an authorization bypass flaw (CVE-2021-29441) and forging a valid JSON web token (JWT) using Nacos's default signing key. Additionally, using its root database access, the LLM injected a backdoor administrator into the Nacos backing database. It ultimately encrypted all 1,342 Nacos service configuration items using MySQL's built-in AES encryption function, and created an extortion demand, ransom note, Bitcoin payment address, and a Proton Mail contact [...]. However, according to the threat hunters, the victim can't recover the encrypted data, even if they paid the ransom demand, because the agent escalated "from row-level deletion to dropping entire database schemas, narrating its own targeting rationale," without backing up any of the encrypted data.

Read more of this story at Slashdot.

"Another breach at Tata has leaked details about Apple's iPhone 18, along with documents belonging to several other Tata clients," writes Longtime Slashdot reader Ritz_Just_Ritz. "It's becoming a recurring theme for the company." Reuters reports: Reuters has previously reported the Tata Electronics leak of more than 200,000 files on the dark web by World Leaks had files with purported component design papers of older iPhones and some parts of Tesla -- both Tata clients. They also included documents of Taiwan Semiconductor Manufacturing Co and Qualcomm, both of which make parts used in iPhones. New documents reviewed by Reuters show there are at least six files that map many components in the iPhone 18 Pro models to the specific company that supplies them. These include details of chips on its main circuit board and parts of the battery and cameras. Apple considers this detail sensitive and is concerned about the documents being shared on the dark web as they relate to unreleased models, according to the person familiar with the matter. The data maps suppliers to iPhone parts, which Apple does not disclose in its public database of suppliers, the person added. In all, the documents detail hundreds of parts to be on the upcoming iPhone 18 Pro models. The records also show where Apple draws a part from several suppliers and where it relies on just a few, laying bare both its bargaining leverage and its vulnerabilities. More broadly, the leak threatens Apple's trust in Tata just as Tata is becoming central to its effort to shift iPhone production away from China. With India expected to produce roughly a quarter of the world's iPhones in 2026, any deterioration in that relationship could complicate Apple's diversification strategy and force tighter security controls across its suppliers.

Read more of this story at Slashdot.

A 29-year-old bug in the Squid web proxy, dubbed Squidbleed and tracked as CVE-2026-47729, can let an authorized proxy user retrieve fragments of another user's cleartext HTTP requests, including credentials and session tokens. The security researcher who reported the flaw credited Anthropic's Claude Mythos Preview for the discovery. The Hacker News reports: Squid describes this as an attack by a trusted client: someone already permitted to use the proxy, not any random host on the internet. That matches Squid's usual home, shared networks like schools, offices, and public Wi-Fi. In those setups, the attacker is just another user of the same proxy. The leak also only reaches traffic that Squid can read. Normal HTTPS rides an opaque CONNECT tunnel, so Squid never sees inside it; the exposed traffic is cleartext HTTP, plus TLS-terminating setups where Squid decrypts and inspects. The attacker also needs the proxy to reach an FTP server they control on port 21. Both FTP and that port are on by default. [...] If you patch, verify the fix, not just the version. Confirm the guard is in FtpGateway.cc, or check your distribution's backport, since distros ship their own builds (Debian packages Squid 5.7). The public thread is still inconsistent: maintainer Amos Jeffries first said Squid 7.6 carried the fix, then corrected that to 7.7, and on June 22 Debian's Salvatore Bonaccorso noted the referenced commit looks like it is already in 7.6. The fix is small, a null-terminator check before the vulnerable strchr calls, merged to the development branch in April and v7 in May. Squid 7.6 does separately patch CVE-2026-50012, an unrelated cache_digest heap overflow. The cleaner move is the one the researchers recommend anyway: turn FTP off. Chromium dropped FTP years ago, and most networks carry almost none of it, so disabling it removes this attack surface for free, whatever build you run. The risk is real but bounded. SUSE rates it moderate, CVSS 6.5, and the vector explains the score: the attacker needs proxy access (low privileges), and the only impact is confidentiality, nothing on integrity or availability.

Read more of this story at Slashdot.

The Wall Street Journal reports on internet-connected devices — and how every year millions of them "can contain a secret digital backdoor that opens up access to your home internet, so that anyone... can surf the web as if they were you." (And this is especially true for "knockoffs that you buy online"...) In a video report this week they tested two digital picture frames from Amazon and three streaming devices from Walmart "because we heard that they often ship with backdoor software used in cyberattacks. Security experts believe manufacturers are being paid to add this malware, but many people also get tricked into downloading the software onto their phones or computers... Within minutes of turning the devices on, there was a surge of internet traffic... Visits to gambling, porn, cryptocurrency and loads of other sketchy web sites started pouring in from users around the world." (And remote visitors also tried to access Outlook and Gmail accounts...) Residential proxy companies even rent out access to "tens of millions of home networks around the world," according to the report. "But the problem is actually worse than that. Hackers figured out a way to seize control of these backdoors, and they started taking over these residential networks. Last month authorities arrested a 23-year-old Ottawa man, saying he'd taken control of more than a million devices to launch some of the largest cyberattacks anyone had ever seen.." After a couple months the Journal's reporter collected logs of all the traffic, and sent it to an investigator at Comcast, who said both were conducting DDoS attacks. But estimate for the number of infected devices are as low as tens of millions or as high 500 million-plus. "We've seen nation state attacks launched through these kind of endpoints, which means your device sitting in your house is part of a nation state attack against another nation state... We've seen ad fraud, we've seen ticket scalping, we've seen financial fraud." But more importantly, "We have seen some of the largest computer attacks — meaning computers attacking other computers at human request — ever recorded in our digital history in the last several months." At cybersecurity conferences, some are warning "there are much larger ones on the horizon if we don't get a hold of this problem." The company making the picture frame "couldn't be reached for comment," while Amazon said it's been out of stock since last year. Both Amazon and Walmart said they take action when they confirm malware on a third-party product.

Read more of this story at Slashdot.

Ars Technica's senior security editor reports: Microsoft says it has detected new self-propagating malware that spreads through USB drives in search of cryptocurrency credentials, which it then sends to attacker-controlled servers. The company named the worm Crypto Clipper because it monitors the contents of device clipboards for patterns consistent with wallet addresses or seed phrases. When found, the malware also takes five screenshots over a 10-second period... "The execution of this clipper is notable because it does not depend on a traditional installer or exposed IP-based C2 infrastructure," Microsoft said Thursday. "Instead, it deploys a portable Tor client, routes traffic through a local SOCKS5 proxy, and blends data theft with remote code execution, turning a financially motivated stealer into a lightweight backdoor." Microsoft said it observed Crypto Clipper spreading through .lnk file on a USB drive. These files store executable code. When an infected USB drive is plugged into a device, the code checks whether it is already installed on the machine. If it isn't, the malware downloads it through the Tor proxy. To better conceal evidence of the worm, the malware scans the infected USB drive and names the .lnk files with similar names... The stealer also replaces addresses it finds with ones belonging to attacker-controlled wallets. This allows the malware to divert payments to the attacker's pockets. Microsoft believes the purpose of the screenshots is to provide context that may be useful. "This malware family shows how lightweight, script-based stealers can deliver outsized impact when paired with anonymized communications and runtime tasking," Microsoft said. "The combination of Tor-routed C2, clipboard targeting, screenshot capture, and remote code execution gives attackers both immediate monetization paths and continued control over compromised devices." Thanks to Slashdot reader joshuark for sharing the news.

Read more of this story at Slashdot.

Researchers have disclosed a new unpatchable BootROM exploit affecting Apple devices with A12, A13, S4, and S5 chips. The attack requires physical USB access and DFU mode, but can let an attacker run code before iOS loads, bypass signature checks, and boot modified software. 9to5Mac reports the details: In a highly detailed technical post published today, the Paradigm Shift Team details usbliter8, a new exploit that "leverages both a hardware bug in the USB controller and a specific configuration flaw present in the device firmware" and cannot be patched. The PS Team explains that ahead of today's disclosure, it shared its findings and worked with Apple Product Security to coordinate the release. The researchers also thanked Apple's security team for its "prompt response, constructive engagement, and cooperation throughout" the process. In a nutshell, this bug affects the following Apple SoCs: A12, S4, S5, and A13. [...] They add that "technical support for A12X/Z is possible," but "it is not currently implemented." That could add the 2018 and 2020 iPad Pro lineups to the list. The way usbliter8 works is: it sends specially crafted data to a device over USB while it is in DFU mode, confusing the USB controller and causing it to write data to the wrong part of memory. That gives an attacker with physical access to the device control over its startup process. From there, they can run their own code before iOS loads, bypass signature checks, and boot modified system software. Importantly, the exploit does not affect or compromise the device's Secure Enclave, which in practice means that data such as passcodes and encrypted user data remain secure. That said, PS Team says that "although usbliter8 doesn't affect SEP itself, it opens up wider attack vectors to compromise the Secure Enclave," adding that "by releasing this exploit publicly, we hope to highlight the real-world impact of these hardware flaws and contribute to a broader understanding of modern SecureROM security." [...] Given that this is also an unpatchable exploit, the researchers note that "affected users should be aware that migrating to newer hardware remains the most effective mitigation."

Read more of this story at Slashdot.

wiredmikey shares a report from SecurityWeek: Microsoft on Wednesday published an advisory acknowledging the public disclosure of a vulnerability in Defender that could lead to privilege escalation. The security defect, tracked as CVE-2026-50656 (CVSS score of 7.8), was dropped last week by security researcher Nightmare Eclipse (also known as Chaotic Eclipse). "We are working to provide a high-quality security update that addresses this vulnerability. We will provide information in this CVE when the update is available," Microsoft adds. RoguePlanet, Nightmare Eclipse explained last week, targets a race condition in Microsoft Defender and allows attackers to gain System privileges. The researcher released a proof-of-concept (PoC) exploit that demonstrates local privilege escalation (LPE) on Windows 11 and Windows 10 systems with the June 2026 patches installed. [...] On Wednesday, Nightmare Eclipse pointed out that the PoC works regardless of whether Defender's real-time protection is enabled or disabled. It may even work in passive mode, the researcher said.

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: A group made up of dozens of cybersecurity experts, including several well-known veterans of the industry, published an open letter to the U.S. government asking it to lift the export control order on Anthropic's Fable and Mythos models. According to the open letter, "this action has taken the best models away from [cybersecurity] defenders" who now can't use the models to find vulnerabilities and make their software and products more secure. "To pull the best capabilities away from defenders without a good reason when our adversaries are rapidly advancing is dangerous," read the letter. On Friday, the U.S. government ordered Anthropic to limit the export of Fable and Mythos, citing national security concerns, without explaining the specific reasons behind the order, according to Anthropic. In response, the company suspended access to the models to all users worldwide. As of this writing, the letter is signed by 76 cybersecurity experts, including Alex Stamos, former Facebook chief of security; Casey Ellis, the founder bug bounty platform Bugcrowd; Jon Callas, famed cryptographer and former Apple security design and architecture manager; Paul Vixie, computer scientist ; Dino Dai Zovi, the former head of applied security engineering at Block; Katie Moussouris, the founder of Luta Security; and Rachel Tobac, the CEO of the security awareness training firm SocialProof Security. [...] Anthropic said that the White House export control order may have been based on a report that there was a method to bypass -- or jailbreak -- Fable to unlock its powerful Mythos-level capabilities. According to Katie Moussouris, one of the signatories of the open letter, the method was demonstrated by Amazon researchers in a paper that is not public but that she has reviewed. But Moussouris said in a blog post that the paper did not actually demonstrate a real jailbreak. Instead, she wrote, the researchers simply asked Fable to fix open source code with public and known vulnerabilities along with "deliberately planted vulnerabilities," after the model initially refused to "review the code for security issues." "The behavior described in the paper cannot meaningfully be fixed, and any attempt would only weaken the model for defense," Moussouris wrote. "Defenders need to be able to ask AI to fix the bugs in a file, explain why the fix matters, and write tests that confirm the patch works. That is not a guardrail bypass. It is the most valuable thing an AI model can do for defensive security: executing the find, fix, and test loop defenders run every day." Moussouris' critique was echoed in the open letter, which also said that the group of experts believe the model capabilities in the Amazon paper "can be replicated" on OpenAI's GPT-5.5, on Anthropic's own publicly available Claude Opus 4.8 and Sonnet, "and even Chinese models like Kimi 2.7." Moussouris told TechCrunch that "the bugs used to demonstrate the techniques in the paper can be found using the other models. The method in the paper is a guardrail bypass technique. Other models that lack the Fable guardrails often won't refuse the straightforward request to look for security bugs, so they don't need a bypass." The letter also asked for transparently and fairly enforced regulations created by "a democratic rule-making process" that are based on scientific research done by industry and academic experts, and "used only to the minimal extent necessary to ensure the safety of the American public."

Read more of this story at Slashdot.