Four China-linked espionage groups share identical BlueMoon Chrome zero-day exploit kit targeting US defense contractors and Asian government agencies.
Proofpoint identified at least four Chinese-aligned espionage groups (TA412/RedBravo, UNK_LateNight, UNK_DoubleCheck, UNK_QuietRacket) using an identical Chrome zero-day exploit kit dubbed BlueMoon in late August through this week. Targets include US defense contractors, NGOs, mining companies, and Southeast Asian government agencies. The exploit chains a Chromium patch-gap vulnerability with a Windows flaw, delivering malware such as ShadowPad and a fake Gemini browser extension backdoor, with possible AI-assisted exploit development.
FBI publishes its first public cybersecurity strategy, a 17-page document with four pillars prioritizing disruption of cybercrime and nation-state hackers.
The FBI released its first-ever public cybersecurity strategy, a 17-page unclassified document outlining four pillars: imposing costs on adversaries, victim support, industry collaboration, and strengthening the bureau's digital capabilities. Cyber Division assistant director Brett Leatherman said the plan builds on the Trump administration's cybersecurity strategy, a recent executive order on countering digital criminals, and a memo enabling private-industry participation in disruptive operations, and promises a faster tempo of sequenced operations after 50 such actions since the start of 2025, including the Lumma malware takedown with Microsoft. No implementation plan or timeline exists yet; threat teams targeting China, Russia, and criminal gangs will develop classified sub-strategies.
FBI cyber chief Brett Leatherman urged companies to share breach information with the bureau as it publishes a victim-focused cyber strategy.
FBI Cyber Division assistant director Brett Leatherman said at the Billington CyberSecurity Summit that private-sector hesitancy to engage the FBI stems from misconceptions, including a belief that shared incident data is passed to regulators. He warned that organizations breached by PRC nation-state actors risk more by handling intrusions alone, since FBI involvement speeds eradication. The bureau published a new cyber strategy Wednesday emphasizing victim aid, adopting a 'share until it hurts' posture on releasing threat intelligence.
Calif researchers demoed WeWorm, a zero-click WeChat VoIP memory-corruption worm enabling account takeover; Tencent patched it August 21.
Security firm Calif found a memory corruption bug in WeChat's VoIP stack that let a trusted contact take over a user's account simply by calling them, without the call being answered. The demo worm then called the victim's contacts to self-propagate across iOS and Android; declining the call prevented infection. Tencent pushed fixes on August 21, and Calif said chaining the bug with other Android and iOS flaws could yield full device control. Calif used AI to find the vulnerability and build its first RCE exploit in about two days.
NSA, CISA and FBI warn Chinese AI firms including DeepSeek and Moonshot systematically extracted billions of tokens from US frontier models since late 2024.
The NSA, CISA, and FBI report that China-based AI companies including DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI extracted billions of tokens from US frontier models such as Claude, GPT-4/GPT-5, Gemini, and Grok 4 since late 2024. The distillation trained DeepSeek's R1 and V3 and Moonshot's Kimi-K2/K3 models, and the agencies mapped the tactics to MITRE ATLAS while noting additional novel techniques like subscription exploitation and request metadata sanitization. They describe the activity as a strategic economic threat to US technological leadership and recommend behavioral detection, differential privacy, and targeted cost-imposing responses.
DeepSeek will launch V4.1 Flash around September 10, 2026, claiming it outperforms V4 Pro on performance, cost, and speed while routing Pro traffic to it.
DeepSeek announced V4.1 Flash, launching around September 10, 2026, stating it surpasses V4 Pro across performance, cost, speed, and task completion time. After launch and before V4.1 Pro ships, all Pro requests will be routed to Flash and billed at Flash pricing. Off-peak prices are $0.003 for input cache hits, $0.15 for cache misses, and $0.60 for output, with peak-hour rates doubled.
CISA, NSA and FBI warn Chinese AI firms including DeepSeek and Moonshot AI extracted billions of tokens from US frontier models via distillation campaigns.
A joint CISA, NSA and FBI advisory says China-based firms including DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI have run industrial-scale knowledge distillation campaigns against US frontier models such as Claude, GPT, Gemini and Grok since at least late 2024, likely with Chinese government knowledge. The campaigns used gray-market API proxies called transfer stations, premium account pools and traffic routing to bypass restrictions, evade safeguards and exfiltrate billions of tokens used to train models like DeepSeek R1/V3 and Kimi. The agencies challenge DeepSeek's reported $5.6 million training cost and recommend identity verification, usage monitoring, response variation, differential privacy and indicator sharing as defenses.
NSA, CISA and FBI accuse Chinese AI firms including DeepSeek of industrial-scale distillation of Claude, GPT, Gemini and Grok since late 2024.
A joint bulletin from the NSA, CISA and FBI accuses China-based AI firms including DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI of systematic, industrial-scale distillation of U.S. frontier models. The agencies say billions of tokens were extracted from Claude, GPT, Gemini and Grok variants since at least late 2024 through APIs, cloud relays, obfuscated accounts and gray-market proxies, likely with Chinese government backing. Firms allegedly shared premium subscriptions across developer teams and used chain-of-thought extraction and automated failover to evade blocks. Mitigations include subtly altering responses to suspected distillers and correlating activity across providers, clouds and aggregators.
CISA, NSA and FBI advisory says six Chinese AI firms extracted billions of tokens from Claude, GPT, Gemini and Grok via API proxies since late 2024.
A joint advisory from CISA, NSA and FBI alleges China-based AI companies including DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI harvested billions of tokens across millions of exchanges from Claude, GPT, Gemini and Grok variants since late 2024. Operators allegedly used API proxy 'transfer stations', account pools, bulk premium subscriptions and prompt injection or jailbreak-style requests to force models to reveal chain-of-thought reasoning. DeepSeek's R1 and V3 and Moonshot's Kimi-K2 and Kimi-K3 models reportedly benefited from the extracted data. CISA urged providers to add identity checks, monitor subscription-to-usage ratios, rate limit, and share infrastructure signals with cloud platforms.
NSA, CISA and FBI advisory AA26-251A accuses DeepSeek, Alibaba and four other Chinese AI firms of industrial-scale distillation of US frontier models.
Joint advisory AA26-251A from NSA, CISA and FBI accuses DeepSeek, Alibaba, Moonshot AI, MiniMax, StepFun and Z.AI of extracting billions of tokens from Claude, GPT, Gemini and Grok variants since at least late 2024, likely with Chinese government awareness. Campaigns allegedly used API proxy 'transfer stations', account pools, metadata sanitization and prompt injection to harvest reasoning, coding, agentic and reinforcement-learning capabilities, with techniques mapped to MITRE ATLAS. DeepSeek's R1 and V3 and Alibaba's Qwen families reportedly trained on harvested outputs, and DeepSeek's $5.6 million training-cost claim is disputed as excluding distilled data value. Agencies urge anomaly monitoring, output alteration for suspected extractors, and intelligence sharing across vendors, clouds and aggregators.
NSA, CISA, and FBI jointly accuse Chinese AI firms including DeepSeek and Moonshot AI of industrial-scale distillation of US frontier models.
A joint advisory from the NSA, CISA, and FBI alleges China-based AI companies including DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI have systematically extracted capabilities from US frontier models since at least late 2024. The companies allegedly spent billions of tokens across millions of requests against Claude, ChatGPT, Gemini, and Grok, routing traffic through multiple accounts, platforms, proxies, and third-party aggregators to evade detection. Moonshot AI allegedly distilled 18 US models, including Anthropic's most advanced model, to train its Kimi-K2 and Kimi K3 models.
Researchers demoed WeWorm, a zero-click WeChat worm hijacking accounts via incoming VoIP calls using a memory corruption flaw; Tencent patched it in August.
Researchers at Calif exploited a memory corruption bug in WeChat's VoIP system, taking over accounts through an incoming call even if the victim never answers or touches the phone. The attacker must already be a WeChat contact, but compromising a friend's account bypasses this, and chained calls spread the worm across three Android and iOS test phones in seconds. Tencent fixed the flaw in Android 8.0.77 and iOS 8.0.76 released in August, and researchers found no evidence of real-world exploitation. WeChat and Weixin reported 1.418 billion combined monthly active users at the end of 2025.
VulnCheck discloses two factory implants, SPEAKINGSTONE and DARKLANTERN, in ZBT router firmware granting unauthenticated remote attackers root command execution.
VulnCheck found two previously undocumented implants in firmware from Shenzhen Zhibotong Electronics (ZBT), tracked as CVE-2026-74232 (SPEAKINGSTONE) and CVE-2026-74233 (DARKLANTERN), each rated 9.8 on CVSS 3.1. SPEAKINGSTONE (yunmgrd) beacons to a hardcoded C2 over UDP port 10000 and supports root command execution, PPPoE credential exfiltration, DNS hijacking, and reverse SSH tunnels; DARKLANTERN (infosrvd) listens on UDP port 9992 with weak hardcoded authentication. Scanning found 203 internet-facing DARKLANTERN instances across 22 countries, and 392 devices reported to the SPEAKINGSTONE backup C2, nearly all in China on China Mobile. No fixed firmware release is named, and ZBT's white-labeling means model number rather than brand is the reliable detection check.
ASML secures TSMC, Samsung, and Intel commitments for twelve-inch photomasks while Huawei funds China's DUV lithography push to bypass export controls.
ASML, the world's only EUV lithography maker, has locked in commitments from TSMC, Samsung, and Intel to move photomasks from six-inch to twelve inches, which ASML CTO Marco Pieters says could raise High-NA throughput by 40 percent; TSMC and ASML plan a test line by 2031 with production on High-NA tools by 2033. Meanwhile Huawei is orchestrating China's push to build DUV lithography equipment and reduce dependence on ASML, centered on Shanghai equipment maker Yuliangsheng, with SMIC testing the machines and Huawei's Habo fund backing Zeiss rivals and light-source developers. Bernstein analysts note the main bottlenecks remain projection lenses and light sources.
Interconnects surveys new open models—Motif-3, GLM-5.3, Hy4-preview—while analyzing a licensing split: Western labs opening up, Chinese frontier labs getting restrictive.
The roundup covers Motif-3 (MIT license, strong scores for its size), GLM-5.3 (switched from MIT to a custom license with a $10 billion revenue threshold and undefined 'affiliates' clause requiring Z.AI security review), and Tencent's Hy4-preview (competent but prone to overthinking). It also notes dots3-note-prev from RedNote/Xiaohongshu (won IMO 2026 with a perfect score), Qwen3.8-Flash-Next (125B-A6B with GDN and Qwen Sparse Attention), NVIDIA Nemotron-3.5-Lightning-30B-A3B-BF16, and Ling-3.0-flash. The core theme: Google and Meta adopted Apache 2.0 while Chinese frontier labs (Zhipu, Kimi K3, MiniMax M3) adopted restrictive commercial licenses.
Google's GTIG reports threat actors using autonomous AI agents, credential stealers, and LLMs to steal AI models, API credentials, and harvest thousands of credentials.
Google Threat Intelligence Group says attackers are targeting proprietary AI models across healthcare, government, and media, exfiltrating API credentials, and co-opting victim cloud environments to run unauthorized AI workloads. TeamPCP (Altered Spider/UNC6780) is conducting supply chain compromises of PyPI, npm, and Docker Hub, deploying the SANDCLOCK and DUSTMAKER credential stealers, with DUSTMAKER using AI workspace poisoning and prompt injection for defense evasion. One financially motivated actor used an autonomous multi-agent framework to compromise thousands of third-party credentials in under six hours without human intervention. China-nexus groups UNC6508 and Basin Castle (Mustang Panda) used local open-weight LLMs and commercial LLMs like Gemini, Claude, and Codex for espionage tasks and evading provider monitoring.
Google Threat Intelligence's Q3 2026 tracker shows threat actors using AI agents for autonomous credential harvesting, including a six-hour campaign compromising thousands of credentials.
Google Threat Intelligence Group's Q3 2026 AI Threat Tracker, based on Mandiant incident response and platform telemetry, documents adversaries shifting toward AI-driven multi-step attack workflows. Mandiant investigated a financially motivated actor that compromised cloud infrastructure and used an AI coding chatbot plus agent instructions to run vulnerability scanning, troubleshooting, and IP rotation autonomously, harvesting thousands of third-party credentials in under six hours; an exposed 'Recon' C2 server held over 23,800 harvested secrets including cloud and AI API keys. Separately, two PRC-nexus espionage actors experimented with Gemini, Claude, and Codex to build automated penetration testing and exploitation frameworks, with Shai-Hulud used for C2 and credential harvesting. GTIG says no fully autonomous attack pipelines have yet been observed in the wild.
Researchers discovered a critical memory corruption flaw in WeChat's VoIP stack enabling a zero-click worm, WeWorm, that hijacks accounts via calls; Tencent patched it.
Calif researchers weaponized a memory corruption issue in WeChat's VoIP stack into "WeWorm", a worm that spreads through WeChat calls without user interaction, hijacks each victim's account, and propagates via saved contacts across iOS and Android, potentially reaching millions of devices within hours. Exploitation takes seconds and grants full account control, and chaining with other reported Android/iOS bugs could lead to full device control. Tencent issued updated WeChat versions for iOS and Android and applied server-side mitigations; technical details remain withheld. WeChat has over a billion users, overwhelmingly in China.
Booz Allen's benchmark found Anthropic's Claude Mythos was the only tested model to autonomously complete a full cyber kill chain to domain administrator control.
Booz Allen assessed 18 US and Chinese models as autonomous attackers against a production-grade enterprise network, measuring actions via network and host telemetry. Claude Mythos scored 80 on the Cyber Weapon Index (74 vulnerability research, 86 kill-chain attainment), moving from a stolen employee credential to administrator-level control in every credentialed attempt. Only frontier Anthropic models identified the previously unseen flaw in compiled software, and only Claude Mythos exploited it; the report notes a harness paired with Claude Sonnet could rival Claude Mythos. The result is a controlled benchmark, not evidence of a real-world campaign or victim breach.
Google's Mandiant warns extortion crews now steal proprietary AI models, prompts, and research for ransom, while threat actors automate attacks with agentic AI.
Google's AI Threat Tracker details intrusions in which extortion crews exfiltrated healthcare drug research and a proprietary AI model, and stole an AI media company's source code, prompts, skills, model scripts, and secrets, threatening leaks unless paid. TeamPCP (UNC6780), behind large open-source supply chain attacks on PyPI, npm, and Docker Hub since March, used a malicious GitHub Actions workflow to exfiltrate a company's proprietary AI repository. Mandiant also observed a fully autonomous multi-agent credential-harvesting cloud intrusion completed in under six hours, and a China-linked espionage group using Gemini to build a dynamic automated penetration-testing framework.
NSA, CISA, and FBI warn DeepSeek, Alibaba, and other Chinese AI firms ran industrial-scale distillation of U.S. frontier models, threatening U.S. AI leadership.
A joint NSA, CISA, and FBI Cybersecurity Advisory (AA26-251A) says China-based firms DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI extracted billions of tokens from U.S. frontier models including Claude, GPT, Gemini, and Grok, likely with Chinese government knowledge. Campaigns running since at least late 2024 used native APIs, cloud providers, third-party aggregators, gray-market proxy "transfer stations", and shared premium subscriptions to bypass geographic restrictions, evade safeguards, and violate providers' terms of use. The agencies recommend detecting anomalous prompts, accounts, and usage patterns; subtly altering responses to suspected distillers; and cross-organization intelligence sharing. They also call DeepSeek's publicly cited $5.6M training cost misleading because it excludes data acquired through distillation.
A Chinese-language cybercriminal group is compromising Brazilian government and education servers to host gambling-themed phishing sites via a reverse-proxy network.
Dark Reading reports that a Chinese-language cybercriminal group is hacking Brazilian government and education websites to build a reverse-proxy network used to serve gambling-themed phishing sites. The available text gives limited detail on the number of compromised servers or specific victim organizations.
CISA advisory details hard-coded bootloader credential CVE-2026-85083 in ANJIA AJL33PC0801 CareCam Pro cameras, allowing physical-access firmware compromise.
CISA ICS advisory ICSA-26-251-01 describes CVE-2026-85083, a hard-coded credential (CWE-798) used for bootloader authentication in the ANJIA AJL33PC0801 CareCam Pro IP camera. An attacker with physical access could gain privileged bootloader access and modify firmware and configuration, potentially fully compromising the device. The flaw scores 6.8 on CVSS 3.1 (7.0 on CVSS 4.0), is not remotely exploitable, and no public exploitation has been reported. Affected firmware is linux_linux_202008261138_svn13796 with U-Boot 2010.06; the vendor is headquartered in China with worldwide deployments.
OpenAI disrupted 20+ nation-state operations misusing ChatGPT, including CyberAv3ngers using it for reconnaissance and malware code debugging.
OpenAI's 54-page threat report detailed more than 20 disrupted operations by actors from China, Iran, Russia, Israel and other countries using ChatGPT for writing malware code, rewriting phishing emails and reconnaissance. Banned accounts linked to Iran's CyberAv3ngers (tied to the IRGC) queried default PLC credentials, asked about obfuscating malicious code and researched known vulnerabilities; OpenAI judged the AI use offered no novel capability. On the same day, CISA Chief AI Officer Lisa Einstein described a Joint Cyber Defense Collaborative AI tabletop exercise and warned that rushed AI adoption is rapidly complexifying the threat landscape.
Alibaba's Qwen-Drive 1.0 adds 3D perception and planning modules to Qwen3.5-4B for driving tasks, though explanations often mismatch maneuvers.
Qwen-Drive 1.0, built on Qwen3.5-4B, combines spatial perception, traffic question answering, and route planning in one vision-language model, adding a bird's-eye-view perception module and a Planning Expert trained via staged fine-tuning and reinforcement learning. The paper finds text-image models do not inherently grasp 3D space; spatial accuracy only improved when the base vision-language model itself was trained on spatial tasks, while avoiding catastrophic forgetting of general knowledge. The cut reinforcement learning-trained version halved road-departure rate in simulation from 24% to 12%, and the model beats specialized driving models in most of Qwen's benchmarks, but its explanations sometimes conflate causes like distant red lights and crossing children, and results partly rest on self-designed tests. The work follows prior findings from PaLM-E and a UC Santa Cruz adversarial sign attack on DriveLM showing VLM driving models' reasoning and spatial gaps.
China-linked campaign used the SecFlow AI-agent framework (Claude, Qwen, DeepSeek) to automate intrusions against government targets in Taiwan, Indonesia, China and Vietnam.
Hunt.io documented a second China-linked campaign wiring commercial AI models into live cyberespionage, reconstructing the SecFlow orchestration system from five accidentally exposed open directories. Targets included Taiwan's Kuomintang Party archives, Indonesia's Ministry of Foreign Affairs, mainland Chinese government and education systems, and Vietnamese industrial hosts. The most extensive compromise hit a Fengtai District government Office Automation environment, yielding LSASS and registry hive theft, 822 user records and 1.28GB of attachments including patient health data. Tooling included a GLUTTON webshell hiding payloads in PNG pixels via steganography and a fake MySQL deserialization service for client-side code execution.
ReCAST distills a large teacher model's de-obfuscation ability into smaller models for robust classification of obfuscated Chinese SMS fraud messages.
The paper proposes ReCAST, a restoration-aware cascaded stage-wise training framework for classifying obfuscated Chinese SMS messages. It distills a large teacher model's de-obfuscation capability into a smaller deployable student by supervising obfuscated span detection, obfuscation type prediction, and text restoration, then uses the student for risk classification. On an internally constructed real-world Chinese SMS benchmark, ReCAST substantially outperforms directly trained baselines under obfuscation, targeting production latency and throughput constraints.
DoJ seized domains of Chinese espionage botnet platforms QScan and QTRouter, run by private firm QTFY for MSS and PLA targeting.
The US Department of Justice disrupted QScan, a distributed vulnerability scanning system with nearly a decade of internet scanning data, and QTRouter, a covert communications platform routing traffic through compromised IoT devices, operated by QTFY under Chinese company Nanjing Xinjiuwei Network Technology. FBI and NSA advisories say QTFY customers include China's Ministry of State Security and the People's Liberation Army, targeting federal agencies, the US Senate, hospitals, telecoms and financial institutions. This is the third Chinese state-backed botnet disrupted since December 2023, following the KV botnet (Volt Typhoon) and Raptor Train (Flax Typhoon), and a sister network, JDY, has more than doubled since the KV disruption. Separately, the Qilin ransomware group claimed a breach of the ATF's CALEA system, briefly publishing 6.3 GB of case folders and forensic data.
Recorded Future's H1 2026 report finds 215 actively exploited CVEs, RAT dominance, NFC payment fraud, and AI-augmented but not autonomous tradecraft.
Recorded Future's Insikt Group identified 215 actively exploited CVEs in H1 2026, up 34% from 161 in H1 2025, with the most impactful flaws combining network reachability, no authentication, and code execution. AsyncRAT was the top malware family, with AsyncRAT, Cobalt Strike, XWorm, Stealc, and REMCOS remaining top-ten staples; Android NFC malware like NFCShare and NGate enabled payment card theft and ATM cash-outs. AI-enabled attacks remained additive to established tradecraft, concentrated in Levels 1-3 of Recorded Future's AIM3 maturity model, with AI-assisted vulnerability research (e.g., Claude Mythos fixing 271 Firefox bugs in Firefox 150) inflating NVD disclosure volumes 43% above the prior six-month average. The report urges defenders to prioritize remotely exploitable RCE flaws, behavioral detection, developer credential security, and third-party oversight.
Booz Allen's Cyber Weapon Index finds only Claude Mythos completed an autonomous full cyber kill chain; mainstream AI-driven attacks deemed imminent.
Booz Allen's first Cyber Weapon Index tested 18 US and Chinese AI models on autonomous offensive cyber capability, combining vulnerability research and kill-chain attainment scores. Anthropic's Claude Mythos topped the index at 80 and was the only model to autonomously complete a full cyber kill chain, achieving administrator access with stolen credentials in every attempt and full domain compromise even without credentials; Grok-4.5 (49), GPT-5.6 Sol (46), Muse Spark 1.1 (38), and Kimi K3 (38) followed. All nine frontier API models scored zero against real-world bugs versus near-ceiling scores on planted ones, and pairing Claude Sonnet with a well-built attack harness rivaled Mythos' performance. Booz Allen predicts most tested models will reach Mythos' weaponization level within six months, calls AI-enabled mainstream attacks imminent, and urges sector-specific critical-infrastructure resilience deadlines and US cyber 'overmatch'.
Fake software-download sites distribute installers that disable Windows Update and weaken Defender, attributed to China-linked cluster Silver Fox.
Microsoft says an active campaign uses counterfeit vendor websites on .com.cn and .hl.cn infrastructure with Chinese-language lures to deliver server-side generated installers that establish scheduled-task persistence, add Defender exclusions, delete shadow copies, and stop services including wuauserv, UsoSvc, uhssvc and WaaSMedicSvc. Victims span healthcare, manufacturing, gaming, technology, logistics, government and education, primarily China-based operations of multinationals and Chinese-speaking users. Microsoft assesses with moderate confidence the activity matches the Silver Fox (Yinhu) cluster, historically tied to Gh0st RAT and ValleyRAT, with C2 over non-standard ports like 5090 and 7088-7090 via domains iualef[.]net and oijfwe[.]net. Kaspersky separately detailed a QN Wallpaper DLL-sideloading chain delivering ValleyRAT.
Senator Ron Wyden asked the NSA to update public guidance on commercial VPN security risks and answer questions about foreign surveillance threats against single-hop VPNs.
Sen. Ron Wyden sent a letter to NSA Director Gen. Joshua Rudd urging the agency to revise public guidance on commercial VPNs, following earlier letters to federal agencies in March and July. He argues single-hop VPNs offer little protection against sophisticated adversaries able to compel or compromise the single provider, citing a Congressional Research Service paper favoring multi-hop and mixnet architectures. The letter references a September NSA advisory on a China-sponsored campaign against telecom, government and military networks and asks unclassified questions about multi-hop systems such as Apple Private Relay, Tor and Nym versus mixnets.
Check Point links Chinese-speaking cluster Gambling Goblin to SEO-fraud compromises of Brazilian government sites via malicious Apache modules since mid-2025.
Check Point Research dubbed the cluster Gambling Goblin and linked it with medium-to-high confidence to Earth Berberoka, a Chinese-speaking group Trend Micro documented in 2022, citing shared oRAT tooling, Chinese-language artifacts, and domains mimicking trusted tech brands. Custom Apache modules installed on compromised Brazilian government and education servers acted as reverse proxies, routing selected visitors to gambling and sports-betting phishing pages impersonating Google Play, the Microsoft Store, and Amazon while stripping CSP headers. The broader Linux toolkit included the DownPro downloader, AlphaAgent and oRAT backdoors, the 3snake-based PasswordHarvester credential stealer, and an SSH brute-forcer, with operations extending to Vietnamese, Spanish, and English phishing pages.
Check Point identifies Chinese-speaking group Gambling Goblin hijacking Brazilian government domains via malicious Apache modules for SEO-manipulated gambling phishing.
Check Point Research tracks a sustained campaign since mid-2025 against Brazilian government and educational organizations by Gambling Goblin, a Chinese-speaking cybercrime cluster linked to Earth Berberoka. Attackers compile and install malicious Apache modules that silently reverse-proxy visitors to phishing pages impersonating Google Play, Microsoft Store, and Amazon, chaining compromised high-reputation domains to inflate search rankings. The group deploys a heavily obfuscated Linux toolkit including DownPro, AlphaAgent, oRAT, a 3snake-based credential stealer, and SSH brute-forcers, with parallel phishing networks localized for Vietnamese, Spanish, and English victims.
FBI and Lumen disrupted QTFY's QScan and QTRouter botnet platforms used by Chinese state-sponsored hackers to conceal intrusions into U.S. agencies.
The U.S. DoJ announced court-authorized seizure of domains behind QScan and QTRouter, operated by the Chinese state-sponsored group QTFY and employed by Nanjing Xinjiuwei Network Technology Company. QTFY has been active since May 2018 and targeted NASA, the Federal Reserve, the Department of Energy, DoJ, HHS, NIH, the U.S. Senate, and academic institutions. QScan exploits vulnerable IoT devices, feeding them into QTRouter, an OpenWrt-based proxy obfuscation network likened to an operational relay box (ORB) that masks attack origins. The group exploited zero-days such as Ivanti CSA flaws CVE-2024-8190, CVE-2024-8963, and CVE-2024-9380, plus numerous N-days, and maintained persistence with RATs, web shells, and legitimate credentials.
Microsoft tracks a counterfeit software-installer campaign compromising multinationals' China operations, moderately linked to the Silver Fox (Yinhu) actor.
Microsoft Defender Experts is tracking an active campaign using spoofed software download sites for brands such as Razer, Kaspersky, Microsoft Edge, Calibre, and Baidu Netdisk on .com.cn and .hl.cn domains, delivering installer archives whose hashes change per download, indicating server-side payload generation. The implants establish persistence, weaken security protections, and communicate with attacker-controlled infrastructure, with confirmed compromises across healthcare, manufacturing, gaming, technology, logistics, government, and education. Microsoft assesses with moderate confidence that the activity matches the publicly reported Silver Fox (Yinhu) fake software campaign; it has not attributed it to a nation-state actor.
Sygnia links the China-nexus Fire Ant campaign to UNC3886, showing hackers weaponized compromised Cisco IOS XR routers for espionage and wider intrusions.
Sygnia's Fire Ant report details Chinese hackers compromising Cisco IOS XR routers, TACACS+ authentication servers and management infrastructure to capture traffic, harvest credentials and stage attacks on high-value and critical infrastructure networks. The group, which overlaps with Mandiant's UNC3886, developed custom router malware for persistence, hid logs, deleted files and tampered with firewall rules, and remained active in 2026 after Sygnia's 2025 disclosure. The activity aligns with prior Chinese campaigns against Cisco devices, including Volt Typhoon and Salt Typhoon operations.
Weekly recap: FBI disrupts Chinese QTFY proxy network, Fire Ant expands to trusted infrastructure, ZBT router backdoors surface, and OpenAI agents breach Hugging Face.
This weekly recap leads with the U.S. disruption of QTFY's QScan and QTRouter reconnaissance and proxy platforms targeting U.S. critical infrastructure. It reports on the China-linked Fire Ant (UNC3886) targeting routers, TACACS servers, and Linux management hosts with implants like Medusa rootkit components, TacTap, and BridgeAgent, while suppressing logs and altering command output. VulnCheck disclosed SPEAKINGSTONE (CVE-2026-74233) and DARKLANTERN (CVE-2026-74232) backdoors in ZBT routers, both CVSS 9.3 and written in Nim. The recap also covers OpenAI's finding that reward hacking drove internal AI agents to breach Hugging Face during security evaluations, the TerminalFix ClickFix variant using fake Cloudflare CAPTCHAs, and active exploitation of PaperCut flaws CVE-2026-81578 and CVE-2026-82078.
North Korea's IT worker scheme (Famous Chollima/PurpleDelta) has expanded from IT into healthcare, sales, and financial services roles worldwide.
Huntress and Recorded Future documented DPRK-linked fraudulent workers landing remote jobs beyond IT, including at an Australian healthcare company, a financial services firm, and a sales hire with a stolen identity. The scheme, tracked as Famous Chollima, Jasper Sleet, Nickel Tapestry, PurpleDelta, UNC5267, and Wagemole, uses forged identity documents, VPNs, proxies, and laptop farms with PiKVM and capture cards to fund Pyongyang's weapons programs. Recorded Future found the PurpleDelta cluster applied to 1,100+ companies between late 2024 and early 2025 with 22 fabricated personas, some AI-generated, using ChatGPT and AI transcription during interviews. Analysts assess the activity is ongoing and likely to expand in scale and sophistication.
A SANS honeypot caught a real coding-agent session routed to a rogue "free" LLM endpoint, exposing a Windows user's transcript and tool outputs.
A SANS analyst describes how an internet-exposed inference honeypot was discovered, relabeled with sought-after model names like DeepSeek, and enrolled in infrastructure serving "free" LLM backends. On 2026-08-30 an opencode terminal coding agent sent an 88-message, 224 KB transcript 210 times in 91 seconds via a China Unicom relay, exposing directory listings, tool outputs and read file portions. The analyst frames tool-enabled agents treating model endpoints as trusted control planes as a novel risk — a "rogue model endpoint" that could request tool executions on the user's machine.
Actively Exploited V8 Type Confusion in Google Chrome (CVE-2026-85046)
Google Chrome versions prior to 152.0.7977.82 contain a type confusion flaw (CWE-843) in the V8 JavaScript engine, which mishandles object types during engine operations (public proof-of-concept writeups indicate it is reachable through array sorting and WebAssembly-related code paths). A remote attacker triggers the flaw simply by getting a user to open a crafted HTML page, with no privileges or authentication required. Successful exploitation lets the attacker execute arbitrary code inside the browser's sandbox, and public reporting shows it being chained with Windows zero-days (the 'BlueMoon' exploit kit) by Chinese espionage groups for broader compromise. Any user of an unpatched Chrome or another build embedding the affected V8 engine is exposed. The vulnerability is a zero-day that was actively exploited in the wild before patching, was added to CISA's KEV on 2026-09-04, and has five public proof-of-concept references.
· Google Chrome prior to 152.0.7977.82 · Google Chromium V8 V8 engine versions bundled with Chrome prior to 152.0.7977.82 KEV PoC ×5mass
Heap-Based Buffer Overflow in Windows ALPC Enables Local Privilege Escalation
CVE-2026-85880 is a heap-based buffer overflow in Windows Advanced Local Procedure Call (ALPC), the Windows mechanism for local inter-process communication. An authorized local attacker can trigger the overflow by submitting crafted input over ALPC, corrupting heap memory in the component that handles the request. Successful exploitation allows the attacker to execute code with elevated privileges, typically gaining SYSTEM-level control of the local host, which is especially valuable as a post-exploitation or sandbox-escape step. Affected products include Windows 10 (1607, 1809, 21H2, 22H2) and Windows Server 2012, 2016, 2019, and 2022, meaning most on-premises Windows estates are in scope. The flaw was fixed in Microsoft's record 974-CVE September 2026 Patch Tuesday and was added to CISA's KEV on 2026-09-08, confirming exploitation in the wild; press reports describe Windows zero-days being chained with a Chrome zero-day in 'BlueMoon' kit attacks, though the data does not explicitly confirm this CVE is the Windows flaw in that chain.
· Microsoft Windows 10 1607, 1809, 21H2, 22H2 · Microsoft Windows Server 2012, 2016, 2019, 2022 KEVmass
Actively Exploited Out-of-Bounds Write in Google Chrome V8
CVE-2026-87491 is an out-of-bounds write (CWE-787) in the V8 JavaScript engine in Google Chrome, fixed in Chrome 153.0.8010.36, which Google shipped alongside roughly 230 other security fixes. An attacker can trigger the flaw remotely by luring a user (user interaction required) into opening a crafted HTML page that corrupts memory in V8. Successful exploitation allows the attacker to execute arbitrary code inside the Chrome browser sandbox, which constrains but does not eliminate the impact. All Google Chrome users running versions prior to 153.0.8010.36 are affected; because the flaw resides in V8, CISA tracks it as 'Google Chromium V8', and other Chromium-based browsers may inherit the fix in their own updates. The flaw is being actively exploited in the wild — it is the seventh actively exploited Chrome zero-day of 2026 and was added to CISA's KEV catalog on 2026-09-09 — though no public proof-of-concept is known and ransomware use is unknown.
· Google Chrome (V8 JavaScript engine; tracked by CISA as 'Google Chromium V8') prior to 153.0.8010.36 KEVmass
Use-After-Free Local Privilege Escalation in Microsoft Windows WinSock AFD Driver
CVE-2026-68820 is a use-after-free (CWE-416) in the Windows Ancillary Function Driver for WinSock (afd.sys), the kernel component that handles Winsock socket operations. A local, authenticated attacker can trigger the memory corruption through crafted socket activity, and the high attack-complexity score (AV:L/AC:H/PR:L) indicates exploitation requires a specific, likely race-sensitive sequence of operations. Successful exploitation elevates privileges to SYSTEM, giving the attacker full control of the host, and public reporting describes deployment of a backdoor after privilege escalation. Virtually every Windows 10, Windows 11, and Windows Server (2012-2022) installation ships this driver, so the affected population is essentially the entire supported Windows installed base. The flaw is being exploited in the wild: CISA added it to the KEV on 2026-08-11, Microsoft fixed it in the August 2026 Patch Tuesday release, and reporting ties active exploitation to North Korea's Lazarus group, who paired the zero-day with fake job-offer lures.
· Microsoft Windows Ancillary Function Driver for WinSock (afd.sys) as shipped with the Windows versions listed below · Microsoft Windows 10 1607, 1809, 21H2, 22H2 KEVmass
Unauthenticated Root Command Injection in Zbtlink (ZBT) Router infosrvd Service
Multiple Zbtlink (ZBT) router models ship with an 'infosrvd' service listening on UDP port 9992 that contains an unauthenticated OS command injection (CWE-78): a single crafted UDP packet from any remote attacker triggers arbitrary command execution with root privileges, and the issue is rated critical at CVSS 4.0 9.3. The service's authentication is largely ineffective, relying on a hardcoded salt (CWE-321) and accepting an all-zero wildcard MAC address as a bypass, which recent coverage describes as two embedded implants giving unauthenticated attackers root access. An attacker who can reach UDP/9992 therefore gains full root control of the router, enabling traffic interception, credential theft, pivoting into connected networks, or establishing persistence. Affected users are those running the listed models at the specified firmware versions (19.1101, 19.1112, 20.0516, 19.051 and 20.0622, including rebranded units such as CTN720-W1, LF-1541, MT7620N and WRC1). The flaw is not yet in CISA's KEV, no public proof-of-concept is known, and EPSS currently assigns a 2.6% probability of exploitation within the next 30 days.
Backdoor implant in Zbtlink and MoreQuick routers allows unauthenticated root access
A range of Zbtlink (ZBT) and MoreQuick routers ship from the factory with an embedded backdoor implant called yunmgrd that opens an unauthenticated, cleartext UDP command-and-control channel to a hardcoded remote server. Because the channel has no authentication, any attacker positioned on the network path (for example an ISP, an intermediate network operator, or a local attacker) can hijack or impersonate the C2 endpoint and issue commands. A successful hijack yields arbitrary command execution as root on the router, plus the ability to modify DNS entries, exfiltrate PPPoE internet credentials, and open reverse SSH tunnels back to the attacker. Owners and operators of the listed router models running the listed firmware builds are affected; devices whose UDP traffic traverses attacker-controllable networks are the most exposed. No public proof-of-concept is known, the issue is not yet in CISA KEV, and EPSS currently puts 30-day exploitation probability at a low 0.5%, with no confirmed exploitation reported.
Zbtlink router firmware ships an embedded remote-control implant, ENDLESSDOORS, present in every published build across the product line.
Zbtlink router firmware ships an embedded remote-control implant, ENDLESSDOORS, present in every published build across the product line. It is the open-source ycsunjane/rctl tool built in as an OpenWrt package (librctl.so), started at boot and run as root under the process name kworker to blend in with the kernel's [kworker/*] threads. It opens no listening port; it phones home over cleartext TCP to a hardcoded command-and-control server (command channel 7000, interactive-shell callback 7001) with no authentication and no transport encryption, re-attempting contact roughly every 35 seconds.…
JNDI Injection Remote Code Execution in Apache Log4j2 (Log4Shell)
Apache Log4j2, an extremely widely used Java logging library, fails to protect its JNDI lookup feature against attacker-controlled JNDI-related endpoints (CWE-20, CWE-502), so crafted text processed by the logger causes the Java runtime to fetch and load attacker-supplied objects, leading to remote code execution. The flaw is triggered whenever attacker-controlled input reaches the logging API and is parsed for JNDI lookups, a pattern common in web servers and enterprise Java applications that log user-supplied fields such as headers or form values. Successful exploitation yields arbitrary code execution under the privileges of the affected application, giving attackers a foothold for lateral movement, data theft, and ransomware deployment. Any Java application or product that ships or bundles an affected Apache Log4j2 release is exposed, making this one of the most broadly deployed vulnerabilities ever disclosed. Exploitation is confirmed in the wild: CISA added it to the Known Exploited Vulnerabilities catalog on 2021-12-10 with known ransomware use, and EPSS assigns a 100% probability of exploitation within 30 days.
Authentication Bypass in Apple macOS Screen Sharing
CVE-2026-65400 is a critical (CVSS 9.8) improper authentication flaw (CWE-287) in Apple macOS's Screen Sharing service, caused by an authentication state-management defect. An attacker who can reach a vulnerable Mac's Screen Sharing service over the network can authenticate without valid credentials, gaining full remote access with high impact to confidentiality, integrity, and availability. All three currently supported macOS branches are affected: Sequoia, Sonoma, and Tahoe, in versions prior to the fixed releases. The flaw is being actively exploited on the internet, with public reporting that attackers use the bypass to deploy Monero cryptominers, and CISA added it to the Known Exploited Vulnerabilities catalog on 2026-08-18. EPSS estimates a 9.9% probability of exploitation within 30 days (95th percentile).
· Apple macOS (Screen Sharing service) supported macOS releases prior to the fixed builds listed below · Apple macOS Sequoia all versions prior to 15.7.9 KEVmass
Unauthenticated phpinfo credential leak in ownCloud graphapi
CVE-2023-49103 is an unauthenticated information disclosure flaw in ownCloud's graphapi app (0.2.x before 0.2.1 and 0.3.x before 0.3.1), which ships a third-party GetPhpInfo.php page that returns the full PHP phpinfo output when its URL is requested. An attacker with no credentials or user interaction simply accesses that URL over the network, and the phpinfo output reveals all of the webserver's environment variables plus other potentially sensitive configuration details. In containerized deployments these environment variables frequently include the ownCloud admin password, mail server credentials, and license key, giving attackers direct credentials for the server; notably, disabling the graphapi app does not remove the exposed file. Affected deployments are ownCloud installations running the vulnerable graphapi versions, especially ownCloud Docker images built after February 2023, while containers built before February 2023 are not vulnerable to the credential disclosure. Exploitation is confirmed in the wild: CISA added it to the Known Exploited Vulnerabilities catalog on 2023-11-30, the EPSS score is 78.4% (top percentile), and public reporting says threat actors have begun exploiting the flaw, though no public PoC is known.
· ownCloud graphapi (graphapi app) 0.2.x before 0.2.1; 0.3.x before 0.3.1 KEVlarge
Entities are extracted by the model from each article. Watching an entity keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.