Check Point details PuzzleMask, a plain-prose technique that bypasses LLM gatekeeper policy checks, letting hidden payloads reach target models unreviewed.
Check Point Research describes PuzzleMask, a prompt-crafting technique that hides policy-violating payloads inside plain-English prose wrappers, bypassing quick LLM-based policy checks without emojis, Base64, or invisible formatting. The researchers tested 23 automated prompts against gatekeepers including GPT-4o-mini, GPT-OSS-Safeguard 20b, Claude 3 Haiku, and Llama Guard 3, and all were classified as safe despite policies that flagged the plain versions. When submitted to GPT-5 in thinking-high mode with a Python interpreter, the target model extracted and acted on the payload in over 90% of trials. The technique is not itself a jailbreak but can carry a jailbreak prompt as payload; mitigations include input paraphrasing, hardened gatekeeper policies, and output monitoring.
Check Point disclosed a covert cross-account channel in OpenAI's internal JFrog Artifactory that let one ChatGPT session exfiltrate another user's connected-app data.
Check Point Research found that OpenAI's internal JFrog Artifactory instance exposed an item management feature allowing one ChatGPT container to attach hidden, Base64-encoded tasks that another user's session would execute with the victim's privileges, such as pulling Gmail emails and exfiltrating them invisibly. Reader credentials granted both read and write access, enabling cross-account task injection. The flaw was reported in late June, and OpenAI had already decommissioned the Artifactory instance following the related Hugging Face intrusion, closing the channel.
Check Point showed a planted prompt could make ChatGPT silently exfiltrate Gmail data via a hidden cross-container channel; OpenAI took the service offline.
Check Point Research demonstrated that a single planted instruction in a ChatGPT conversation could make the model silently exfiltrate Gmail data, chat history, and files to an attacker's account while replying normally to the user. The covert channel abused read/write properties on files in an internal JFrog Artifactory instance shared by ChatGPT code-execution containers across accounts, turning package metadata into shared storage. Injection vectors included pasted prompts, shared conversations, and custom GPT builder instructions; default connected-app permissions allowed Gmail reads without user approval. OpenAI confirmed the internal service was taken offline after disclosure; this is Check Point's second reported ChatGPT covert channel after a DNS-based one fixed in February.
Check Point discovers cross-account data leakage in ChatGPT: isolated code-execution containers communicate via shared JFrog Artifactory, enabling covert Gmail exfiltration.
Check Point Research found a covert bidirectional channel between ChatGPT code-execution containers belonging to different accounts, which were supposed to be isolated from each other and the public internet. Both could reach the same internal JFrog Artifactory instance used for package delivery, whose exposed Item Management API allowed a 'shared clipboard' between containers. In a proof of concept, a hidden instruction in a shared conversation made ChatGPT retrieve email data from the victim's connected Gmail account and send it to the attacker's account while the victim received a normal answer. The same channel could exfiltrate conversation history and session files; OpenAI recently described a similar isolation weakness in its postmortem of the Hugging Face incident.
Check Point details JSCeal, a V8-compiled JavaScript stealer that replays stolen cookies to bypass Google authentication, spread via crypto malvertising.
Check Point Research's new report analyzes JSCeal, a compiled V8 JavaScript malware obfuscated with javascript-obfuscator using RC4-protected strings, control-flow flattening, and proxy functions. Delivered through fake TradingView installers on malvertising sites overlapping the WEEVILPROXY/MeadowLocust and SourTrade campaigns, it harvests cookies, passwords and OAuth tokens from Chromium browsers, records keystrokes and screenshots, and can replay stolen Google session cookies to bypass authentication. It also installs a local proxy with service-specific handlers for Binance, Bybit, and Ledger to intercept and modify cryptocurrency-related traffic.
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's hasherezade details static deobfuscation of JSCeal, a V8-bytecode stealer targeting cryptocurrency applications since March 2024.
JSCeal is an infostealer distributed as compiled V8 bytecode (.jsc) executed by a bundled Node.js runtime, aimed at cryptocurrency applications. Other vendors track the same family under the names WEEVILPROXY or MeadowLocust. Check Point Research has tracked the campaign since early 2024, with activity dating back to March 2024. The write-up presents a static approach to unpacking the bytecode without executing it.
Manchester Airports Group disclosed a cyberattack exposing contact details of about 8.7 million customers across Manchester, Stansted, and East Midlands airports.
Manchester Airports Group, the UK operator of Manchester, London Stansted, and East Midlands airports, disclosed a cyberattack that exposed data belonging to roughly 8.7 million customers. Check Point's weekly threat intelligence bulletin reports the compromised information includes contact details. The disclosure appeared in Check Point's 31 August Threat Intelligence Report covering the week's top attacks and breaches.
Check Point revealed BTR Reforged, a technique weaponizing Microsoft Defender's built-in BTR.sys driver to delete security software at boot without exploiting any vulnerability.
Check Point Research disclosed BTR Reforged, a technique that abuses BTR.sys, a legitimately signed Windows Defender boot-time remediation driver, to perform arbitrary kernel-level file and registry operations on Windows 7 through Windows 11 25H2 without exploiting a software flaw. The BTR_CLI proof-of-concept tool, presented at Black Hat USA 2026 and DEF CON 34, installs the driver via direct registry writes and executes deletions during the boot-time 'golden window' before Defender's user-mode services start, demonstrated by deleting the full Defender stack on a patched Windows 11 machine. Exploitation requires SeLoadDriverPrivilege; Microsoft confirmed it does not meet criteria for immediate servicing and no patch is planned. No evidence of real-world abuse was found, and related indicators of compromise via Sysmon events were published.
Check Point uncovers the StopAndProtect ransomware operation infecting thousands of WordPress sites via ClickFix social engineering and PowerShell downloaders.
Check Point Research first observed the StopAndProtect ransomware family in mid-May 2026 and linked its infrastructure to thousands of hacked WordPress sites. The infection chain begins with ClickFix social engineering that prompts victims to run a PowerShell command, followed by two stages of additional downloaders. The research maps the shared infrastructure unifying the operation.
Microsoft's August Patch Tuesday fixes 398 CVEs, including actively exploited Windows zero-day CVE-2026-68820 used by Lazarus for SYSTEM privilege escalation.
Microsoft's August 2026 Patch Tuesday release addresses 398 new vulnerabilities, 62 rated Critical by the Zero Day Initiative, with CVE-2026-68820 (CVSS 7.0), a use-after-free in the afd.sys Windows kernel driver, the only flaw flagged as actively exploited. Check Point Research attributed exploitation of the privilege escalation bug to Lazarus' Operation Dream Job campaign. Four unauthenticated remote code execution flaws rated 9.8 affect Windows DNS Server (CVE-2026-62878, called wormable by ZDI), Windows Deployment Services (CVE-2026-62893), Microsoft QUIC (CVE-2026-62815) and HPC Pack (CVE-2026-59124). The release also completes a two-part SharePoint fix with RCE component CVE-2026-63520, following July's authentication bypass fix CVE-2026-55040.
Authentication Bypass in Microsoft SharePoint Server
Microsoft SharePoint Server is affected by a weak authentication vulnerability (CWE-1390) that allows an unauthorized attacker to bypass a security feature over a network. Per the CVSS vector, exploitation requires no privileges and no user interaction with low attack complexity, so any unauthenticated attacker with network access to a vulnerable server can trigger it remotely. Impact to confidentiality and integrity is rated high (CVSS 9.1, critical), meaning the bypass effectively grants the attacker access that authentication should have prevented, with no direct availability impact. All organizations running on-premises Microsoft SharePoint Server are potentially affected; the source data does not specify affected version ranges or fixed builds, so defenders should consult Microsoft's advisory for those details. The flaw is under active exploitation: a public proof-of-concept is available on GitHub, attackers began exploiting it after the PoC went public, and CISA added it to the Known Exploited Vulnerabilities catalog on 2026-08-18 (EPSS ~40%, 99th percentile; ransomware association unknown).
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
Use-after-free RCE in Microsoft MsQuic via crafted network packets
A use-after-free (CWE-416) in Microsoft's QUIC implementation (MsQuic) allows an unauthenticated remote attacker to execute code on an affected host. The flaw arises because creating and removing new network paths in response to incoming packets can invalidate a pointer that is subsequently used. An attacker needs only to send a specially crafted packet to a service speaking QUIC, with no authentication or user interaction required; the maximum CVSS 4.0 score of 10 (critical) reflects full system-compromise potential. Any deployment of the MsQuic library is affected, including services built on Microsoft's in-box QUIC support (e.g., HTTP/3 and SMB over QUIC) and applications consuming the public NuGet package, though exact affected version ranges are not specified in the available data. Exploitation has not been observed: there is no public proof-of-concept, the issue is not in CISA's KEV, and EPSS puts the 30-day exploitation probability at about 1 percent, but a fix ('Guard path promotion', commit e0f55b5) is already available.
· Microsoft MsQuic (Microsoft QUIC library; distributed via NuGet) · Microsoft Services and applications using MsQuic (e.g., HTTP/3, SMB over QUIC, .NET System.Net.Quic)mass
Pre-auth use-after-free RCE in Microsoft Windows Deployment Services (WDS)
Microsoft Windows Deployment Services (WDS) contains a use-after-free memory-safety flaw (CWE-416) that an unauthenticated attacker can trigger by sending crafted network traffic to the WDS service, leading to remote code execution on the target system. The vulnerability affects Windows 10 1607 and 1809 and Windows Server 2012, 2016, 2019, 2022, and 2025 on systems where WDS is deployed, a role typically used for network-based (PXE) operating system imaging. A successful exploit grants the attacker code execution with high confidentiality, integrity, and availability impact, reflected in the critical CVSS 3.1 score of 9.8 with network vector, low complexity, and no privileges or user interaction required. No public proof-of-concept, CISA KEV listing, or confirmed in-the-wild exploitation is currently known, although EPSS estimates a 2.7% probability of exploitation within 30 days (85th percentile). The flaw was disclosed alongside Microsoft's record September 2026 Patch Tuesday, which shipped nearly 1,000 fixes including two Windows zero-days.
· microsoft Windows 10 1607 · microsoft Windows 10 1809large
Unauthenticated Deserialization RCE in Microsoft HPC Pack
CVE-2026-59124 is a deserialization of untrusted data flaw (CWE-502) in Microsoft High Performance Computing (HPC) Pack that allows an unauthorized attacker to execute code over a network. Because the vulnerable component processes untrusted serialized input, an attacker who can reach the network-facing service can send malicious serialized data and trigger arbitrary code execution without credentials or user interaction. Successful exploitation grants the attacker the ability to run code in the context of the affected service, with full confidentiality, integrity, and availability impact per the 9.8 CVSS score. Any organization running Microsoft HPC Pack on Windows — typically head nodes and management endpoints of Windows HPC clusters — is affected. As of the August 2026 Patch Tuesday release that addressed it, there is no known public proof-of-concept, no CISA KEV listing, and no confirmed exploitation in the wild, though the EPSS score of 1.7% (76th percentile) suggests a moderate near-term exploitation probability.
· Microsoft HPC Pack (High Performance Computing Pack) on Windowsniche
Unauthenticated Stack Buffer Overflow RCE in Windows DNS (CVE-2026-62878)
Windows DNS contains a stack-based buffer overflow (CWE-121) that an unauthenticated, network-adjacent or internet-reachable attacker can trigger by sending crafted input to the DNS service. Successful exploitation yields remote code execution on the target host, with high impact on confidentiality, integrity and availability (CVSS 3.1: 9.8). The flaw affects the DNS component shipped with Windows 10 1607 and 1809 and with Windows Server 2012, 2016, 2019, 2022 and 2025; systems running the DNS Server role, especially internet-facing DNS servers and domain controllers, are the primary targets. Microsoft, which assigned the CVE, has issued a fix, and the flaw appeared amid a record-sized run of Patch Tuesday releases. No in-the-wild exploitation is currently known: it is not in CISA's KEV, no public proof-of-concept is available, and EPSS estimates only a 1.3% probability of exploitation within 30 days.
· microsoft Windows 10 1607 · microsoft Windows 10 1809mass
Unauthenticated RCE in Microsoft SharePoint Server
CVE-2026-63520 is an improper input validation flaw (CWE-20) in Microsoft Office SharePoint, affecting on-premises SharePoint Server deployments. A remote, unauthenticated attacker can trigger the flaw by sending improperly validated input to the SharePoint service over the network; the high attack complexity (AC:H) indicates exploitation depends on specific conditions, but no privileges or user interaction are required. Successful exploitation results in arbitrary code execution on the server, with high impact to confidentiality, integrity, and availability — effectively full compromise of the SharePoint host. Organizations running self-hosted SharePoint Server are in scope; SharePoint Online/Microsoft 365 is not listed in the affected products. The issue is patched as of Microsoft's Patch Tuesday (headlines mark it FIXED), with Rapid7 analysis and a researcher-disclosed exploit chain available, but there is no public PoC, no CISA KEV listing, and no confirmed in-the-wild exploitation; EPSS puts exploitation probability at 2.9% (86th percentile).
· Microsoft SharePoint Server (Office SharePoint, on-premises)mass
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.