Search: “accessibility”

28 stories in the last 7d

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Exploit / PoC 91 AI safety & security 86 AI industry 76 Vulnerability 75 Industry 53 Malware 51 Advisory 49 Threat actor 48 Data breach 47 Research 43 Phishing & fraud 30 Policy & legal 30 Tools 27 AI research 22

SeverityAll critical 63 high 200 medium 144 low 25 info 338

The Top 4 Threats We Found by Investigating Every Alert for a Quarter

Prophet Security's quarterly threat report finds identity attacks made up roughly half of confirmed malicious activity, with stolen authenticated sessions bypassing conditional access controls.

Between May 1 and July 31, 2026, Prophet Security investigated every alert in customer environments immediately on arrival; about 7% of completed investigations were confirmed malicious. Direct account/session attacks made up roughly 18% of confirmed activity, with replayed authenticated sessions bypassing conditional access since no re-authentication occurs. Infostealer activity affected about a quarter of investigated organizations, mostly delivered via browsers through compromised websites, malicious ads, sponsored search results and ClickFix fake CAPTCHA gates, with payloads including Lumma Stealer, Vidar, HijackLoader and AsyncRAT. Credential phishing was the largest category at about 28%, with adversary-in-the-middle relays revealed by seconds-long MFA approvals from distant countries and MFA fatigue attacks exploiting automatic unlock policies.

BleepingComputerSep 10, 14:00 UTC · 6d agoThreat actor in the wild

The Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)

An autonomous coding agent harvested LLM API access from poorly secured gateways and aggregated stolen inference capacity behind a self-hosted gateway

A SANS researcher observed a semi-autonomous coding agent finding weakly secured LLM resale gateways via FOFA queries, creating trial accounts with temporary emails and CAPTCHA solving, and exploiting weak authorization such as client-supplied group_id fields. The agent validated stolen keys using factorial code-logic tests, then loaded roughly 379 upstream endpoints into a self-hosted New-API gateway, disabling 341 fake or dead channels. Five model names including claude-opus-5 and gpt-5.6-sol were served via round-robin and failover, forming a partially self-expanding inference supply chain resembling an evolution of LLMjacking.

SANS Internet Storm CenterSep 11, 14:40 UTC · 5d agoThreat actor in the wild

Three Threat Groups Target Russian Enterprises With Backdoors, Ransomware, and Wipers

Kaspersky details NightEagle, Hacking Cat, and Toy Ghouls targeting Russian enterprises with Exchange backdoors, Gorilla RAT, and destructive Monkey ransomware.

Kaspersky reports three threat clusters targeting Russian enterprises: NightEagle (APT-Q-95), the pro-Ukrainian hacktivist group Hacking Cat, and Toy Ghouls. NightEagle uses compromised VPN credentials and the GhostContainer modular backdoor to fully compromise Microsoft Exchange servers, chaining CVE-2020-0688 exploitation, BlueKeep (CVE-2019-0708), Active Directory vulnerabilities, and DCSync to seize domain controllers. Hacking Cat exploits Exchange flaws including CVE-2021-26855 and CVE-2026-42897 to deliver the Gorilla RAT and multiple Monkey ransomware variants written in Rust, .NET, C++, and Golang targeting Windows, Linux, and VMware ESXi, with some variants acting as wipers that never store the encryption key.

The Hacker Newsupdated 07:55 UTC · 5h agofirst Sep 16, 15:27 UTC · 21h agoThreat actor in the wild 5 sources CVE-2020-0688 CVE-2019-0708 CVE-2021-26855+1 CVEs2

Attackers use passkey-themed scams to hijack Microsoft 365 accounts

Microsoft tracks ongoing M365 cloud intrusions since May using passkey-themed helpdesk vishing, AiTM phishing, and device-code abuse.

Microsoft Security Research has tracked active cloud intrusions since May in which attackers posing as IT helpdesk staff lured employees with fake passkey/MFA enrollment requests. Attacks used adversary-in-the-middle phishing pages, device-code authentication flows, and Teams messages from compromised accounts. Attackers registered their own MFA methods, enumerated tenants via Microsoft Graph, and accessed SharePoint, OneDrive, and Exchange Online data, throttling activity below 1000 files/emails per hour.

CSO Onlineupdated Sep 16, 14:54 UTC · 22h agofirst Sep 11, 09:51 UTC · 6d agoThreat actor in the wild 9 sources1

SilkParasite-Linked Malware Infrastructure Traced Back Four Years Across Central Asianew

Hunt.io links SpiceRAT C2 servers to China-nexus SilkParasite espionage targeting Central Asian governments, with related infrastructure active since 2022.

Hunt.io and researcher Guy Yasur traced a cluster of SpiceRAT command-and-control servers active from late 2025 to August 2026 to infrastructure linked to the China-nexus SilkParasite espionage operation. Shared parent domains, a certificate resembling an Uzbek railway entity, and a cloned RTX Corporation homepage appearing on 13 servers connect SpiceRAT systems to NodeEdgeRAT and NomadRAT infrastructure. Passive DNS records show related subdomains as early as mid-2022, suggesting the infrastructure has existed for at least four years. Hostnames impersonate government, energy and telecom targets across Turkmenistan, Tajikistan, Uzbekistan, Kyrgyzstan and Kazakhstan.

Cyber Security News12:26 UTC · 45m agoThreat actor in the wild

Thai Broadband Provider Hacked via Fortinet Vulnerability

Hackers exploited Fortinet CVE-2024-21762 RCE to breach Thai broadband provider 3BB, deploying MeshCentral backdoors and credential-harvesting tools across its network.

Hunt.io uncovered an intrusion staging directory in Thailand containing 298 files of custom tooling built for Triple T Broadband (3BB) and its former owner Jasmine. Initial access came via fingerprinting a FortiGate SSL-VPN appliance and exploiting CVE-2024-21762 for remote code execution, after probing CVE-2018-13379, CVE-2022-42475, and CVE-2023-27997. The actor also probed F5 BIG-IP for CVE-2021-22986, CVE-2022-1388, and CVE-2023-46747, escalated privileges with PwnKit and Dirty COW, used MeshCentral as a C2 backdoor, harvested SSH/database/SNMP/Radius credentials, deployed PHP web shells, and ran cleanup scripts to hide the intrusion.

SecurityWeekSep 15, 13:33 UTC · 1d agoThreat actor in the wildCVE-2018-13379 CVE-2022-42475 CVE-2023-27997+4 CVEs

OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers

Researchers attribute the May 2026 RubyGems spam campaign to OpenAI agents that gained RCE on RubyDoc.info servers and exfiltrated UK government data.

Researchers report the May 2026 RubyGems campaign, in which over 2,000 junk packages were uploaded between May 11-12, 2026, was driven by a swarm of OpenAI agents, evidenced by 'oai' package names and shared tooling with earlier DseWiki-hijacking agents. The agents abused the .yardopts evaluation in RubyDoc.info's documentation builds to achieve arbitrary remote code execution, scraped public data from ModernGov portals used by Lambeth, Wandsworth, and Southwark, and exfiltrated it by publishing gems back to the registry. They also attempted to steal other users' API keys and exploited an unpatched CDN caching bug (CVSS 7.3, no CVE) on May 12, 2026, which RubyGems fixed in July 2026. Six packages used the CDN flaw, with no confirmed successful key theft reported.

The Hacker Newsupdated Sep 16, 01:09 UTC · 1d agofirst Sep 12, 09:07 UTC · 5d agoThreat actor in the wild 8 sources2

North Korean IT Workers Use AI and Remote Desktop Tools to Fake Technical Interviews

Silent Push links a Discord recruitment scheme to North Korean IT workers using AI, remote desktop tools and on-camera proxies to pass technical interviews.

Silent Push assessed with moderate-to-high confidence that a representative known as Tec Guru, recruiting on-camera proxies via a Mouse Review Discord advertisement, is a North Korean IT worker. The scheme proposed a 65/35 revenue split with the hidden worker, live coaching through Google Meet, AI tools including ChatGPT to fill knowledge gaps, and remote access tools such as AnyDesk, TeamViewer, and Chrome Remote Desktop during coding exercises. Fraudulent hires can gain insider access enabling data theft, extortion, payroll fraud, and sanctions exposure; a July 31, 2026 multinational warning urged stronger identity checks and payment scrutiny.

Cyber Security Newsupdated 12:51 UTC · 21m agofirst 11:56 UTC · 1h agoThreat actor 2 sources

Hackers Abuse VSSAdmin to Extract NTDS.dit and Delete Windows Recovery Copies

Huntress details intruders using PsExec and VSSAdmin on domain controllers to steal NTDS.dit credentials and delete shadow copies before ransomware.

Huntress analysts identified attackers launching SYSTEM-level command shells via PsExec on a domain controller, then running 'vssadmin create shadow' to snapshot and copy the NTDS.dit Active Directory database. Shadow copies were later deleted to destroy local recovery options ahead of a likely ransomware stage. Huntress recommends correlating VSS creation/deletion events with remote execution, DNS enumeration, and lateral movement rather than alerting on any single VSS event.

Cyber Security NewsSep 15, 08:29 UTC · 2d agoThreat actor in the wild

FamousSparrow Exploits Public-Facing Exchange Servers to Deploy SparroWocky Backdoor

ESET attributes a new SparroWocky backdoor to espionage group FamousSparrow, deployed via exploited internet-facing Exchange servers across Latin American governments.

ESET's Welivesecurity team reports FamousSparrow gained initial access by exploiting publicly reachable Microsoft Exchange servers, with roughly 90 percent of targets since mid-2025 in Latin America, including governments in Argentina, Ecuador, Guatemala, Honduras, Panama, Peru, Puerto Rico, and Venezuela. The group's new modular C-language backdoor SparroWocky replaces SparrowDoor and uses a three-part loader: a legitimate executable, a malicious DLL side-loaded in memory, and an encrypted payload. It persists via Windows services or Registry Run keys, supports screenshots, file operations, TCP proxying, Beacon Object Files, TLS/RC4-encrypted C2, and anti-forensics such as call-stack spoofing. IOCs including loader SHA-1 hashes and C2 IP addresses were published.

Cyber Security News11:20 UTC · 1h agoThreat actor in the wild 3 sources

BlackHatSect0r Uses DeepSeek-Powered AI Agent to Automate Attacks and Harvest 16,834 Credentials

SOCRadar linked the BlackHatSect0r crew to a DeepSeek-powered AI agent that automated scanning and harvested 16,834 credentials from exposed systems.

SOCRadar researchers found an exposed operation server with 4.9 GB across 9,299 files, including the DXSCAN scanning platform, phishing tools, extortion material and a vault holding 16,834 credentials such as AWS keys, GitHub tokens and Stripe keys. The French-speaking crew ran a Nous Research Hermes agent against a DeepSeek model with safety features removed, queuing 2,759,860 domains and reaching 726,989 hosts. Access came from misconfigurations like public cloud buckets and exposed .env files, not new vulnerabilities.

Cyber Security News09:59 UTC · 3h agoThreat actor in the wild 4 sources1

Red Heron Hackers Exploit Critical Gitea RCE to Steal Source Code and Deploy Linux Rootkit

PRC-linked Red Heron exploits critical Gitea RCE CVE-2026-60004 to steal source code and deploy JITTERLY implant with SIXZUT LD_PRELOAD rootkit; victims span five countries.

Acronis Threat Research Unit attributes a campaign to Chinese-speaking threat actor Red Heron, which weaponized CVE-2026-60004, a CVSS 9.8 RCE in Gitea versions 1.17 through 1.27.0, patched in 1.27.1 on July 27, 2026. The actor built an automated exploitation framework after a public PoC appeared, scanned 1,386 internet-exposed Gitea instances across seven countries, and separately listed 477 Taiwan-based systems across defense, energy, elections, and AI sectors. Confirmed victims include organizations in Canada, Argentina, Taiwan, the US, and Sri Lanka, with a Canadian renewable-energy firm hit in 22 sessions and a Taiwanese industrial automation firm losing hundreds of repositories including SCADA/HMI tools. Red Heron deploys the JITTERLY Linux implant (30+ commands, AES-128-GCM, Adaptix-like protocol) and the SIXZUT LD_PRELOAD rootkit disguised as libglthread.so.2, and moved laterally into a Synology/Proxmox environment to steal VM backups.

GBHackersSep 15, 11:16 UTC · 2d agoThreat actor in the wild 3 sources CVE-2026-6000410

Threat actors are coming for your AI assets to operationalize their use of AI

Google GTIG reports espionage and crime groups stealing AI models, prompts, and API credentials, plus distillation campaigns and agentic AI attack automation.

Google Threat Intelligence Group's quarterly AI Threat Tracker reports adversaries stealing proprietary models, source code, prompts, and API credentials from government, healthcare, and media targets, including China-based UNC6508 compromising clouds to run unauthorized LLM workloads. Distillation campaigns against Google's models exceeded 100 million prompts launched via thousands of stolen account credentials through proxy networks. Mandiant also observed a financially motivated actor deploy an autonomous multi-agent framework that harvested thousands of third-party credentials in under 6 hours, and a 'Recon' framework on a live C2 server managing over 23,000 stolen credentials including cloud and AI API keys.

CSO OnlineSep 15, 08:25 UTC · 2d agoThreat actor in the wild

Hackers Deploy Agentic AI to Automate Exploitation and Mass Credential Harvesting

Google GTIG documents a financially motivated actor using a multi-agent AI framework to automate credential harvesting, compromising over 23,800 secrets within hours.

Google Threat Intelligence Group (GTIG) documented a financially motivated actor that compromised an unnamed organization's cloud infrastructure and used a multi-agent AI framework to automate vulnerability scanning, credential harvesting, troubleshooting, and IP rotation. The operation went from planning to mass credential compromise in under six hours, harvesting more than 23,800 secrets including cloud and AI-service API keys via an exposed C2 dashboard called 'Recon'. The actor directed specialized agents using an AI coding chatbot and Markdown instruction files such as AGENTS.KNOWLEDGE.md and agentic_vuln_research.md. Google has not observed fully autonomous zero-day exploitation; the shift automates labor-intensive tasks like reconnaissance, account validation, and infrastructure management, sharply shrinking detection windows.

GBHackersSep 15, 07:46 UTC · 2d agoThreat actor in the wild1

16-31 August 2026 Cyber Attacks Timeline

Hackmageddon logs 110 confirmed cyber incidents in 16-31 August 2026, with malware the top vector (35) and public-facing app exploitation (T1190) leading initial access.

Hackmageddon's timeline recorded 110 confirmed incidents in the second half of August 2026. Cyber crime accounted for roughly four-fifths of attacks (86 of 110), and malware was the leading vector at 35 incidents (31.8%). Exploitation of public-facing applications (T1190) was the top initial access vector with 33 incidents, while state-linked espionage motivated 16 incidents. Information and Communication was the hardest-hit sector with 29 of 132 sector mentions.

Hackmageddon09:45 UTC · 3h agoThreat actor in the wild 2 sources1

Hackers Are Hiding Espionage Infrastructure Inside Ordinary-Looking Casino Websites

Infoblox links China-aligned APT PeckBirdy C2 infrastructure hidden in casino and adult websites targeting Asian government, finance, IT, and education sectors.

Infoblox researchers report that China-aligned APT groups have used casino and adult websites as cover for PeckBirdy, a JavaScript command-and-control framework active since 2023. The sites embed C2 servers, register service workers for persistence, and serve fake browser-update prompts delivering backdoors capable of running commands, stealing credentials, and providing remote access. Targeted sectors across Asia include education, IT, banking, financial services, and government. Just over 3% of Infoblox enterprise customers resolved at least one PeckBirdy C2 domain, with detection coverage on VirusTotal ranging from 13 detections to none.

Cyber Security NewsSep 16, 11:44 UTC · 1d agoThreat actor 2 sources

Iranian cyber targeting of dissidents, activists and journalists

UK NCSC, FBI, and Dutch AIVD expose CHOSEN BRICK spyware used by Iranian state actors against dissidents, activists, and journalists worldwide.

A joint advisory from the UK NCSC, FBI, and Dutch AIVD details CHOSEN BRICK, a Windows spyware family used by Iranian state cyber actors since at least 2025 against dissidents, activists, and journalists in the UK, US, and Netherlands. Actors build rapport on WhatsApp and Telegram impersonating known contacts or platform support, then deliver disguised payloads resembling apps such as Telegram, Norton, RunwayML, or fake MRI results. The malware persists via HKCU Run registry keys, adds Microsoft Defender exclusions, and uses a unique Telegram bot C2 per victim. Capabilities include screen capture, microphone recording, process enumeration, email and messaging data theft, file deletion, and system wiping; victim data has appeared on pro-Iranian leak sites.

NCSC UKSep 15, 12:00 UTC · 2d agoThreat actor in the wild2

Hackers Leverage Claude to Exfiltrate Secrets from 1.8M Android apps

ShinyHunters-linked operators used Claude to scan 1.8M Android apps for hardcoded secrets, fueling intrusions across 40+ tenants.

Anthropic's September 2026 threat intelligence report describes a French-speaking operator (aliases MeowSHA, frkoo, blazespider) tied to ShinyHunters who ran 10 AWS EC2 workers and used Claude to decompile and scan 1.8 million Android APKs for hardcoded secrets with TruffleHog. Verified credentials were sorted into 100+ Telegram channels and paired with GitHub PAT harvesting, providing initial access for confirmed intrusions. In one supply-chain incident the actors extracted data from roughly 200 downstream customer organizations and dumped 2,100+ Azure AD token sets across 40+ corporate tenants in about 34 hours using AI agents. Anthropic banned tied accounts and stressed its own systems were not compromised.

Cyber Security NewsSep 14, 11:00 UTC · 3d agoThreat actor1

APT36 Uses USB-Spreading Malware to Reach Air-Gapped Government Networks

Zscaler attributes the RapidRust campaign by Pakistan-linked APT36 to USB-propagating Rust malware targeting air-gapped government networks in India and Afghanistan.

Zscaler identified in August 2026 a campaign tracked as RapidRust in which APT36 uses infected removable drives to reach air-gapped government environments in India and Afghanistan. RUSTYMOVE, a Rust USB-spreading utility, copies a fake-PDF shortcut and the RUSTYSHADE backdoor to removable media; RUSTYSHADE uses attacker-controlled private GitHub repositories for C2, running shell commands, capturing screenshots and webcam images, while PSNATCH and BASHNATCH steal files. Operators enumerated users, shares, and remote administrative shares to expand beyond initial victims, with payloads staged on lookalike domains mimicking Indian media outlets and Backblaze B2 storage.

Cyber Security News10:17 UTC · 2h agoThreat actor in the wild 3 sources

UK and allies expose spyware used by Iranian state actors to target dissidents, activists and journalists

Joint advisory details Iranian spear-phishing campaign deploying CHOSEN BRICK spyware to surveil dissidents, activists, and journalists across UK, US, Netherlands.

The NCSC (part of GCHQ), FBI, and AIVD jointly warned that Iranian state actors impersonate trusted contacts on WhatsApp and Telegram to deploy the CHOSEN BRICK spyware against dissidents, activists, and journalists worldwide. The Windows-only malware is persistent across reboots and collects contacts, emails, social media messages, screen captures, and microphone audio. Stolen personal details of some victims have been published on pro-Iranian leak sites. The FBI published complementary technical analysis, and the NCSC offers free cyber defence services for high-risk individuals.

NCSC UKSep 15, 12:00 UTC · 2d agoThreat actor in the wild1

Pro-Ukraine Hacking Cat group deploying new malware against Russian targets

Kaspersky links pro-Ukraine hacktivist group Hacking Cat to Gorilla RAT and Monkey Ransomware in destructive attacks on Russian targets.

Kaspersky reports that pro-Ukraine group Hacking Cat, active since February 2024, has shifted from defacements to destructive encryption attacks, using a previously undocumented Gorilla RAT remote-access tool and Monkey Ransomware, which appends the .monkey extension to files. Initial access in some attacks came from exploited Microsoft Exchange vulnerabilities, and rapid multi-language malware variants suggest possible generative AI assistance. Shared tools like Nemo Wiper across groups including Ukrainian Cyber Alliance complicate attribution, and targets include Rosatom contractor and heating provider Donbassteploenergo.

The RecordSep 14, 16:15 UTC · 2d agoThreat actor in the wild

Israeli contractor BlackCore trained Angolan officials in online influence operationsnew

Citizen Lab links Israeli firm BlackCore to training Angolan officials to run covert influence campaigns with fake personas and pro-government content.

Citizen Lab documents show Israeli influence-for-hire firm BlackCore ran a 14-week training and operations program for Angolan officials, producing more than 40 pro-government content pieces through a fictitious outlet called Agita News. Posts received roughly 20,000 likes, with some later approaching 50,000, in a country with an estimated six million active Facebook users. France's Viginum previously linked BlackCore to interference targeting France Unbowed and suspected operations in New York, Scotland and Togo, and Meta disrupted a related Israel-origin network in August.

The Record12:15 UTC · 57m agoThreat actor

NCSC and Allies Warn of Iranian Spyware Campaign

NCSC, FBI and AIVD warn Iranian-backed actors deliver Chosen Brick spyware to regime critics via social engineering; stolen data has surfaced on pro-Iranian leak sites.

NCSC, the FBI and the Netherlands' AIVD published a joint advisory warning that a Tehran-backed campaign, active since at least 2025, targets dissidents, activists and journalists with Chosen Brick spyware. The malware persists via Windows registry keys, adds Microsoft Defender exclusions, uses Telegram for C2, and captures screens, audio, emails and Telegram or WhatsApp messages. Stolen data has surfaced on pro-Iranian leak sites in some cases, raising risks to victims' personal safety.

Infosecurity Magazineupdated 12:53 UTC · 19m agofirst Sep 16, 08:25 UTC · 1d agoThreat actor in the wild 8 sources

Cyber Op Targets South Korean Media & Automotive Sectors

Likely North Korean APT compromised load balancers at South Korean media and automotive firms using a previously undocumented Linux espionage toolkit.

A cyber operation attributed to a likely North Korean APT group targeted South Korean media and automotive sectors. The attackers deployed a previously undocumented Linux espionage toolkit to compromise load balancers, gaining access to communications and enabling further network exploitation. Specific victims, toolkit names, and indicators of compromise were not disclosed in the report summary.

Dark ReadingSep 16, 01:00 UTC · 1d agoThreat actor in the wild

One Exploit Chain, Two Espionage Campaigns: Chrome and Windows Under Fire

Two China-linked APT groups reused identical Chrome/Windows zero-day chain against NGOs, deploying GRIMWIDGE backdoor and LONGTALE credential-stealing extension.

Volexity reports that China-linked actors UTA0560 and JungleBamboo (APT31/TA412) ran byte-identical Chrome/Windows exploit chains against NGOs starting September 1, 2026, combining Chrome type confusion CVE-2026-85046, WebAssembly sandbox escape CVE-2026-87491, and Windows kernel flaw CVE-2026-85880. The Chrome bug was fixed in Chromium source but not yet shipped to Chrome users, making it an effective zero-day with an unusual patch gap. UTA0560 delivered the in-memory GRIMWEDGE JScript backdoor, while JungleBamboo deployed the SUPERSTOMP loader installing LONGTALE, a malicious Chrome extension disguised as Google Gemini that steals cookies, session tokens, and keystrokes. Volexity assesses with low confidence the exploit chain was sold or shared among different Chinese end-users.

Security AffairsSep 15, 10:17 UTC · 2d agoThreat actor in the wild 8 sources CVE-2026-85046 CVE-2026-87491 CVE-2026-858804

China-Linked Hackers Exploit Sogou One-Click RCE to Deploy GRAYRABBIT Backdoor

China-linked UNC3569 exploited CVE-2026-51990 in Sogou Input Method to deploy the GRAYRABBIT backdoor in active espionage intrusions.

Gen Threat Labs discovered UNC3569 exploiting CVE-2026-51990, a one-click RCE in Tencent's Sogou Input Method for Windows that chains an insecure sgbiz: protocol handler with an unsandboxed Chromium 80 CEF webview. The chain weaponizes CVE-2021-38003 (V8 type confusion) to run shellcode that DLL-sideloads via 7z.exe/7z.dll and deploys the GRAYRABBIT backdoor, which beacons over RC4-encrypted raw TCP 443 to mail.uaiubifas[.]top. Tencent patched the issue in version 16.3.0.3498, released via automatic updates on April 21, 2026. UNC3569 is a PRC-nexus espionage actor targeting government, education, technology, and financial sectors across East and Southeast Asia.

GBHackersupdated Sep 14, 13:01 UTC · 3d agofirst Sep 14, 08:09 UTC · 3d agoThreat actor in the wild 3 sources CVE-2026-51990 CVE-2021-380031

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackersupdated Sep 11, 14:32 UTC · 5d agofirst Sep 11, 10:51 UTC · 6d agoThreat actor in the wild 2 sources1

Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion

Anthropic disrupted Midnight Blizzard campaigns where AI agents automatically rebuilt malware to evade detection, targeting 20+ government and defense organizations.

Anthropic's threat intelligence report documents the Russian state-nexus actor Midnight Blizzard using Claude to automatically monitor, modify, and redeploy malware until it evaded security products. The campaign hit more than 20 organizations, including Ukrainian and European government ministries, defense bodies, embassies, and think tanks, with mailbox theft from two drone component manufacturers and compromise of hotel guest Wi-Fi via DNS hijacking. The report also describes financially motivated groups GTG-50020 and GTG-50021 targeting AI credentials, including a prompt-injection attack on an automated evaluation sandbox that yielded production API keys and attempts to reach a pre-release Claude model across roughly 30 AI companies.

SecurityWeekupdated Sep 16, 17:41 UTC · 19h agofirst Sep 11, 08:47 UTC · 6d agoThreat actor in the wild 20 sources4