threat-intel Agentjacking Attack Tricks AI Coding Agents Into Running Malicious Code A new attack method, dubbed ‘Agentjacking,’ is exploiting vulnerabilities in AI coding agents like Claude Code and Cursor by tricking them into executing malicious code through crafted error reports sent via Sentry. This… The Hacker News · Jun 12, 2026 High aiagentjackingsentry
threat-intel LangGraph Flaw Chain Exposes Self-Hosted AI Agents to Remote Code Execution A critical vulnerability chain in LangGraph, an open-source AI agent framework, has been disclosed, allowing for remote code execution via SQL injection and unsafe deserialization. The flaws, affecting versions prior to… The Hacker News · Jun 12, 2026 Critical CVE-2025-67644CVE-2026-28277CVE-2026-27022USsql injectionremote code executionai agent
data-breach Over 73,000 French govt employees affected in Tchap messenger breach A breach of the French government’s Tchap messaging platform has affected over 73,000 employees within the public sector. The attackers exploited a compromised user account to access public chat room data, including name… BleepingComputer · Jun 12, 2026 High FRmessagingdata breachencryption
threat-intel New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets A research report highlighted vulnerabilities in OpenClaw, a popular self-hosted AI agent, revealing that attackers could trick the agent into running malicious code or leaking sensitive data by embedding instructions wi… The Hacker News · Jun 11, 2026 High USaiagentprompt injection
threat-intel Segmentation Works for OT If Operators Are Paying Attention This Dark Reading article highlights the ongoing challenges of operational technology (OT) security, particularly concerning network segmentation. Despite the widely recommended practice of isolating systems to limit dam… Dark Reading · Jun 11, 2026 High ot securitynetwork segmentationcybersecurity
data-breach Coupang hit with record $409 million data breach fine in Korea Coupang, a major South Korean e-commerce company, has been hit with a record $409 million fine by the Personal Information Protection Commission (PIPC) due to a massive data breach affecting over 37 million customers. Th… BleepingComputer · Jun 11, 2026 High SOCHdata breachauthenticationdata security
threat-intel AI Broke Vulnerability Management. That's Why CISOs Are Moving Budget to BAS. The rapid advancement of AI, particularly through tools like Anthropic's Claude Mythos Preview, has dramatically reduced the time it takes to discover and exploit vulnerabilities in software. This has collapsed the tradi… The Hacker News · Jun 11, 2026 High USGBaivulnerabilityexploitation
threat-intel Smashing Security podcast #471: This AI worm just rewrote its own rules This episode of Smashing Security discusses an AI worm that is capable of rewriting its own rules, highlighting a concerning trend of AI systems exhibiting unexpected and potentially malicious behavior. The conversation… Graham Cluley · Jun 10, 2026 High USaiartificial intelligenceworm
supply-chain The ‘Miasma’ worm source code briefly leaked on GitHub The source code for the Miasma credential-stealing worm framework, previously linked to supply-chain attacks targeting open-source ecosystems, was briefly leaked on GitHub. This leak, mirroring the earlier Shai-Hulud wor… BleepingComputer · Jun 10, 2026 High USsupply chaincredential theftopen source
threat-intel CISA to require federal agencies to patch some cyber vulnerabilities within 3 days CISA has issued a new binding operational directive requiring federal civilian agencies to patch critical cybersecurity vulnerabilities within a tight 72-hour timeframe, prioritizing those exposed to the internet and sus… The Record · Jun 10, 2026 High USvulnerabilitypatchingai
threat-intel The 5 Best Practices for Secure Identity Verification This article from BleepingComputer highlights key best practices for organizations to strengthen their identity verification processes and improve overall cyber resilience. It emphasizes the growing threat of credential… BleepingComputer · Jun 10, 2026 High UKmfaidentity verificationauthentication
vulnerability Microsoft Patches Record 206 Flaws, Including Three Zero-Days and Critical RCE Bugs Microsoft released a significant security update addressing 206 vulnerabilities across its software portfolio, including multiple critical Remote Code Execution (RCE) flaws and several zero-days. The update focuses on pa… The Hacker News · Jun 10, 2026 Critical CVE-2025-10263CVE-2026-8863CVE-2026-45657USzero-dayrcebitlocker
threat-intel Blame AI: Patch Tuesday Hits Record 206 CVEs Microsoft’s June 2026 Patch Tuesday update released a record-breaking 206 CVEs, signaling a potential shift towards larger and more frequent security updates driven by the accelerating pace of vulnerability discovery fac… Dark Reading · Jun 9, 2026 High CVE-2026-45586CVE-2026-49160CVE-2026-50507USvulnerabilityzero-dayai
threat-intel Microsoft Exchange Flaw Lets Attackers Spoof Any Email Address This article details a vulnerability in Microsoft Exchange, dubbed "Ghost-Sender," that allows attackers to spoof any email address by exploiting misconfigurations in Exchange Online and on-premises hybrid environments u… Dark Reading · Jun 9, 2026 High email spoofingexchangephishing
supply-chain GitHub disables Microsoft repos pushing password-stealing malware Microsoft repositories on GitHub were temporarily disabled on June 5th due to concerns about distributing malware, specifically linked to the ongoing Miasma/Shai-Hulud supply-chain campaign. The incident involved the com… BleepingComputer · Jun 9, 2026 High USsupply-chain attackgithubmalware
threat-intel Claude Mythos Turns N-Days Into N-Hours With Rapid Exploit Creation Anthropic’s Claude Mythos AI model has demonstrated the ability to rapidly generate working exploits for known vulnerabilities in software like Firefox and Windows, significantly accelerating the attack process. The mode… SecurityWeek · Jun 9, 2026 High USaiexploitationn-day
malware Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models Researchers at the University of Toronto have developed a novel AI-driven computer worm that operates autonomously by leveraging locally hosted, open-weight large language models. The worm dynamically generates attack st… The Hacker News · Jun 9, 2026 Critical CVE-2026-39987CVE-2026-31431CVE-2026-43284GBaiwormllm
data-breach French govt messaging service breached in account hijacking attack The French government’s Tchap messaging service was breached after a compromised user account was used to gain access, leading to the theft of sensitive data including user information and over 13.5GB of files. The attac… BleepingComputer · Jun 9, 2026 High FRsocial engineeringdata theftmessaging
threat-intel New FROST Attack Lets Websites Track What Sites and Apps You Open via SSD Timing A new attack method, dubbed FROST, allows websites to track which sites and apps a user opens by analyzing the timing of SSD reads. Developed by researchers at Graz University of Technology, FROST leverages the Origin Pr… The Hacker News · Jun 9, 2026 High DEopfsssdtiming attack
vulnerability Google patches new Chrome zero-day flaw exploited in the wild Google has released a security update to address a newly discovered and actively exploited zero-day vulnerability (CVE-2026-11645) within the Chrome browser. This flaw, originating in the V8 JavaScript engine, allows att… BleepingComputer · Jun 9, 2026 High CVE-2026-11645CVE-2024-0519CVE-2026-2441zero-daychromev8
