vulnerability Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers A vulnerability in Amazon Kiro, an AI-powered IDE, allows attackers to steal sensitive data by injecting malicious prompts and leveraging Kiro Powers. This flaw, currently unpatched, could lead to significant data breaches within organizations using the Kiro IDE. The Hacker News · 3d ago Medium prompt-injectionaiide
ransomware Gunra ransomware: what you need to know The Gunra ransomware gang is aggressively targeting organizations across multiple sectors, leveraging unpatched VPNs and firewalls to gain access and deploy their ransomware. They are demanding payments to decrypt stolen… Graham Cluley · 6d ago High vpnfirewallransomware
threat-intel New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data Adversa AI has discovered a technique called "Cryptographic Context Injection" that allows an attacker to steal user data, including names, location, subscription tier, and conversation history, from xAI's Grok chatbot.… The Hacker News · Aug 20, 2026 High prompt-injectiondata-exfiltrationencryption
threat-intel 'CoSnitch' Attack Tricked Copilot into Mapping Out Architecture Researchers discovered a novel 'meta-hacking' technique that tricked Microsoft Copilot Personal into revealing its own security vulnerabilities, allowing attackers to map out its architecture and subsequently steal enter… Dark Reading · Aug 18, 2026 High CVE-2026-24301prompt-injectionmeta-hackingdata-exfiltration
threat-intel Cl0p industrialise ses attaques via PTC Windchill A critical vulnerability in PTC Windchill and FlexPLM has been exploited by the Cl0p group, leading to a widespread campaign targeting nearly 50 international companies, including Philips, Shell, Fiserv, and GE. The vuln… ZATAZ · Aug 13, 2026 High CVE-2026-12569vulnerabilitysupply-chainremote-code-execution
vulnerability Atlassian Rovo Can Be Tricked Into Sending Jira and Confluence Data to Attackers Atlassian’s Rovo assistant has two vulnerabilities that could allow attackers to exfiltrate data. The first, a one-click link flaw, has been patched by Atlassian. The second, a content-borne prompt injection attack, allo… The Hacker News · Aug 8, 2026 High prompt-injectiondata-exfiltrationatlassian
threat-intel CSS: The Hidden Threat Lurking in Your Inbox Researchers have discovered that Cascading Style Sheets (CSS), traditionally used for website design, can be weaponized to steal sensitive data from webmail platforms. While not a new threat, the potential for CSS-based… Dark Reading · Aug 5, 2026 Medium csswebmailsecurity
threat-intel New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands Researchers at Seoul National University, the University of Illinois Urbana-Champaign, and Largosoft have discovered a new attack method called Agent Data Injection (ADI) that can manipulate AI agents by subtly corruptin… The Hacker News · Jul 16, 2026 High CVE-2025-32711prompt-injectiondata-exfiltrationai-security
threat-intel Gamaredon Expands Ukraine Attacks with New Malware and Cloud Service Abuse The Gamaredon APT group continued its aggressive cyberattacks against Ukraine throughout 2025, utilizing a range of new malware and exploiting vulnerabilities to steal sensitive information. The group expanded its tactic… The Hacker News · Jun 29, 2026 High CVE-2025-8088RUUAspear-phishingpersistencecloud-services
vulnerability DifyTap Bugs Let Attackers 'Wiretap' AI Chat Histories A series of vulnerabilities, dubbed "DifyTap," have been discovered in the Dify AI application building platform, allowing attackers to potentially access and exfiltrate sensitive data, including AI chat histories. The f… Dark Reading · Jun 22, 2026 High CVE-2026-41947CVE-2026-41948CVE-2026-41949aisecurityvulnerability
supply-chain Cybersecurity Firms Impacted by Klue Supply Chain Attack A supply chain attack targeting the Klue market intelligence platform resulted in the unauthorized harvesting of customer data from various integrations, including Salesforce and HubSpot. The attack, attributed to a new… SecurityWeek · Jun 19, 2026 High supply-chainoauthcrm
threat-intel Salesforce Disables Klue App Integration After OAuth Token Abuse Exposes Customer Data Salesforce disabled the Klue Battlecards app integration following a security incident where the Icarus extortion group exploited compromised credentials to access customer data via Salesforce. The attackers leveraged a… The Hacker News · Jun 19, 2026 High USoauthcredentialdata-exfiltration
threat-intel ⚡ Weekly Recap: Chrome 0-Day, UniFi Exploits, macOS Stealers, VPN Flaw and More This week’s cybersecurity recap highlights several active exploits and attacks, including a Chrome 0-day being actively leveraged, a ShinyHunters gang exploiting a PeopleSoft zero-day for lateral movement and data exfilt… The Hacker News · Jun 15, 2026 High CVE-2026-11645CVE-2026-2441CVE-2026-3909UNCHzero-dayphishingsupply-chain
threat-intel Hackers pose as women seeking romance to spy on Russian soldiers A previously unknown cyber espionage group, SiribClone, has been targeting Russian military personnel by impersonating women seeking romantic relationships. The group’s primary goal is to gather battlefield intelligence… The Record · Jun 9, 2026 High RUespionagesocial-engineeringmobile-malware
threat-intel China Uses Dual-Method Cyberattack on Czech Orgs This article details a dual-method cyberattack targeting organizations in the Czech Republic and Taiwan, orchestrated by Chinese nation-state threat actors. The campaign, dubbed "Operation Dragon Weave," utilizes a spear… Dark Reading · Jun 2, 2026 High CZCNTWspear-phishingrustazure
threat-intel US charges Google security engineer with Polymarket insider trading A Google security engineer, Michele Spagnuolo, has been charged with insider trading after exploiting confidential ‘Year in Search’ data to profit from bets on the Polymarket prediction market. He used his access to Goog… BleepingComputer · May 29, 2026 High USITSWinsider-tradingconfidential-datacryptocurrency
