[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$frLscXxJSrQ3oyirHs1EchrT-fc2jCdZA3KWbrQ4yV64":3},{"article":4,"iocs":49,"watch_terms":50,"solutions":51,"lesson":121},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"url":11,"image_url":12,"published_at":13,"ingested_at":14,"relevance_score":15,"entities":16,"category_id":33,"category":34,"article_tags":38},"91a5b256-057e-45ea-bbf1-82e53c516011","Gemini Voice Assistant Hijacked via Messaging Notifications","gemini-voice-assistant-hijacked-via-messaging-notifications-1c8779","Attackers could have triggered dangerous actions, including controlling smart home devices via Google Home and starting Zoom video calls. The post Gemini Voice Assistant Hijacked via Messaging Notifications appeared first on SecurityWeek.","SafeBreach researchers discovered a critical vulnerability in Google's Gemini voice assistant that allowed attackers to inject malicious commands through messaging notifications from apps like WhatsApp, Slack, and SMS. The attack, termed Fake Context Alignment, could enable threat actors to control smart home devices, initiate video calls, craft spoofed messages, and establish persistent control over the assistant. Google patched the vulnerability in mid-November 2025 after disclosure in August 2025.","Google Gemini voice assistant vulnerable to hijacking via messaging notification prompt injections.","https:\u002F\u002Fwww.securityweek.com\u002Fgemini-voice-assistant-hijacked-via-messaging-notifications\u002F","https:\u002F\u002Fwww.securityweek.com\u002Fwp-content\u002Fuploads\u002F2026\u002F04\u002FGemini.jpeg","2026-06-04T12:57:37+00:00","2026-06-04T14:00:28.267421+00:00",9,[17,20,23,25,27,30],{"name":18,"type":19},"Gemini Voice Assistant","product",{"name":21,"type":22},"Google","vendor",{"name":24,"type":19},"Google Home",{"name":26,"type":22},"SafeBreach",{"name":28,"type":29},"Prompt Injection","technology",{"name":31,"type":32},"Fake Context Alignment","campaign","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":33,"icon":35,"name":36,"slug":37},null,"Vulnerabilities","vulnerabilities",[39,44],{"category":40},{"id":41,"icon":35,"name":42,"slug":43},"574f766a-fb3f-487c-8d2c-0720ae75471b","Zero-day","zero-day",{"category":45},{"id":46,"icon":35,"name":47,"slug":48},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",[],[21,26,18],{"controls":52,"vendors":110},[53,82],{"slug":54,"name":55,"problem":56,"products":57},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[58,66,74],{"vendor_slug":59,"vendor_name":60,"vendor_logo":61,"product_slug":62,"product_name":63,"url":64,"description":65},"huntress","Huntress","\u002Fvendor-logos\u002Fhuntress.png","managed-edr","Huntress Managed EDR","https:\u002F\u002Fwww.huntress.com\u002Fplatform\u002Fmanaged-edr","Endpoint detection and response monitored around the clock by Huntress analysts.",{"vendor_slug":67,"vendor_name":68,"vendor_logo":69,"product_slug":70,"product_name":71,"url":72,"description":73},"sophos","Sophos","\u002Fvendor-logos\u002Fsophos.png","sophos-endpoint","Sophos Endpoint","https:\u002F\u002Fwww.sophos.com\u002Fen-us\u002Fproducts\u002Fendpoint-security","Endpoint protection with Intercept X anti-ransomware technology and EDR.",{"vendor_slug":75,"vendor_name":76,"vendor_logo":77,"product_slug":78,"product_name":79,"url":80,"description":81},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","defender-for-endpoint","Microsoft Defender for Endpoint","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fendpoint-security\u002Fmicrosoft-defender-endpoint","Endpoint detection and response for Windows, macOS, Linux and mobile devices.",{"slug":48,"name":83,"problem":84,"products":85},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[86,94,102],{"vendor_slug":87,"vendor_name":88,"vendor_logo":89,"product_slug":90,"product_name":91,"url":92,"description":93},"cisco","Cisco","\u002Fvendor-logos\u002Fcisco.png","ai-defense","Cisco AI Defense","https:\u002F\u002Fwww.cisco.com\u002Fsite\u002Fus\u002Fen\u002Fproducts\u002Fsecurity\u002Fai-defense\u002Findex.html","Discovery of AI use, testing of models and guardrails for AI applications.",{"vendor_slug":95,"vendor_name":96,"vendor_logo":97,"product_slug":98,"product_name":99,"url":100,"description":101},"hiddenlayer","HiddenLayer","\u002Fvendor-logos\u002Fhiddenlayer.png","hiddenlayer-ai-security","HiddenLayer AI Security Platform","https:\u002F\u002Fhiddenlayer.com\u002F","Model scanning, AI red teaming and runtime protection for AI applications.",{"vendor_slug":103,"vendor_name":104,"vendor_logo":105,"product_slug":106,"product_name":107,"url":108,"description":109},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","prisma-airs","Prisma AIRS","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fai-security\u002Fprisma-airs","Security for AI applications, models and agents, including runtime protection against prompt injection.",[111,116],{"slug":112,"name":21,"logo_path":113,"roles":114},"google","\u002Fvendor-logos\u002Fgoogle.png",[115],"affected",{"slug":117,"name":26,"logo_path":118,"roles":119},"safebreach","\u002Fvendor-logos\u002Fsafebreach.png",[120],"reported_by",{"slug":122,"title":123,"body":124,"framework_refs":125,"framework_notes":131},"voice-assistant-hijacking-through-notification-injection","Voice Assistant Hijacking Through Notification Injection","Google's Gemini voice assistant contained a critical vulnerability that allowed attackers to inject malicious commands through messaging app notifications, enabling control of smart home devices and persistent access. The 'Fake Context Alignment' attack exploited how the assistant processed notification content, treating external messages as legitimate system commands. This demonstrates how AI-powered systems can be manipulated through unexpected input vectors, potentially giving attackers broad access to connected devices and personal data. Organizations must recognize that voice assistants and AI systems require the same rigorous security testing as traditional applications.",[126,127,128,129,130],"CIS Control 7 (Malware Defenses)","NIST SP 800-53 SI-3","NIST SP 800-53 AC-6","CIS Control 12 (Network Infrastructure Management)","OWASP IoT Top 10",{}]