[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fEIMqWGcBXarF_QuZSYHvJU9sLjOyi69tZ7A5SyEtMP8":3},{"article":4,"iocs":44,"watch_terms":45,"solutions":46,"lesson":136},{"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":26,"category":27,"article_tags":31},"27cea38a-d748-46dd-821c-d7ef0d785d1e","Hackers Could Bypass ChatGPT Lockdown Mode to Steal Conversations Without Users Knowing","hackers-could-bypass-chatgpt-lockdown-mode-to-steal-conversations-without-users-7ad751","A flaw in ChatGPT let attackers slip past Lockdown Mode, the safety setting meant to stop data leaks. Check Point Research found that a hidden pop-up trick could copy a user’s full chat history, show fake windows, and push malware. In the ChatGPT Classic desktop app, simply chatting was enough to trigger the leak. OpenAI […] The post Hackers Could Bypass ChatGPT Lockdown Mode to Steal Conversations Without Users Knowing appeared first on Cyber Security News.","Check Point Research discovered a vulnerability in ChatGPT's Lockdown Mode that allowed attackers to bypass security measures. The flaw could be exploited to steal entire chat histories, display fake update windows to trick users into downloading malware, and capture login credentials. OpenAI has since patched the vulnerability.","ChatGPT Lockdown Mode bypassed by researchers, allowing data leaks and malware delivery.","https:\u002F\u002Fcybersecuritynews.com\u002Fchatgpt-lockdown-mode-bypass\u002F","https:\u002F\u002Fresearch.checkpoint.com\u002Fwp-content\u002Fuploads\u002F2026\u002F10\u002F2-password-phishing-1.mp4","2026-11-06T08:16:23+00:00","2026-11-06T09:00:24.951546+00:00",8,[17,20,23],{"name":18,"type":19},"ChatGPT","product",{"name":21,"type":22},"OpenAI","vendor",{"name":24,"type":25},"AI","technology","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":26,"icon":28,"name":29,"slug":30},null,"Vulnerabilities","vulnerabilities",[32,37,39],{"category":33},{"id":34,"icon":28,"name":35,"slug":36},"2e06f76c-d5b9-4f54-9eef-4d3447b10730","Breaches","breaches",{"category":38},{"id":26,"icon":28,"name":29,"slug":30},{"category":40},{"id":41,"icon":28,"name":42,"slug":43},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",[],[21,18],{"controls":47,"vendors":129},[48,77,102],{"slug":49,"name":50,"problem":51,"products":52},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[53,61,69],{"vendor_slug":54,"vendor_name":55,"vendor_logo":56,"product_slug":57,"product_name":58,"url":59,"description":60},"crowdstrike","CrowdStrike","\u002Fvendor-logos\u002Fcrowdstrike.png","falcon-insight-xdr","Falcon Insight XDR","https:\u002F\u002Fwww.crowdstrike.com\u002Fen-us\u002Fplatform\u002Fendpoint-security\u002Ffalcon-insight-xdr\u002F","Endpoint detection and response with extended detection across other security tools.",{"vendor_slug":62,"vendor_name":63,"vendor_logo":64,"product_slug":65,"product_name":66,"url":67,"description":68},"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.",{"vendor_slug":70,"vendor_name":71,"vendor_logo":72,"product_slug":73,"product_name":74,"url":75,"description":76},"eset","ESET","\u002Fvendor-logos\u002Feset.png","eset-protect","ESET PROTECT","https:\u002F\u002Fwww.eset.com\u002Fint\u002Fbusiness\u002Fsolutions\u002Fendpoint-protection\u002F","Endpoint protection platform with detection and response add-ons.",{"slug":43,"name":78,"problem":79,"products":80},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[81,89,97],{"vendor_slug":82,"vendor_name":83,"vendor_logo":84,"product_slug":85,"product_name":86,"url":87,"description":88},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","boomi-ai-gateway","Boomi AI Gateway","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fai-gateway\u002F","Gateway for AI model and MCP tool traffic, built on Lunar.dev technology. It limits which tools each agent can call. Its enterprise version adds an approval step for new MCP servers and logs each call with the user or agent behind it.",{"vendor_slug":90,"vendor_name":91,"vendor_logo":92,"product_slug":93,"product_name":94,"url":95,"description":96},"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.",{"vendor_slug":82,"vendor_name":83,"vendor_logo":84,"product_slug":98,"product_name":99,"url":100,"description":101},"boomi-agentstudio","Boomi Agentstudio","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fagentstudio\u002F","Agent builder whose Agent Control Tower registers and monitors Boomi agents and agents on Amazon Bedrock, Microsoft Copilot and other platforms, keeps audit logs and can switch agents off where the provider allows it.",{"slug":103,"name":104,"problem":105,"products":106},"security-awareness-training","Security awareness training and phishing simulation","People recognise and report attacks instead of falling for them.",[107,115,122],{"vendor_slug":108,"vendor_name":109,"vendor_logo":110,"product_slug":111,"product_name":112,"url":113,"description":114},"huntress","Huntress","\u002Fvendor-logos\u002Fhuntress.png","managed-sat","Huntress Managed Security Awareness Training","https:\u002F\u002Fwww.huntress.com\u002Fplatform\u002Fsecurity-awareness-training","Security awareness training and phishing simulation, managed for you.",{"vendor_slug":116,"vendor_name":117,"vendor_logo":118,"product_slug":103,"product_name":119,"url":120,"description":121},"knowbe4","KnowBe4","\u002Fvendor-logos\u002Fknowbe4.png","KnowBe4 Security Awareness Training","https:\u002F\u002Fwww.knowbe4.com\u002Fproducts\u002Fsecurity-awareness-training","Training library and simulated phishing with reporting.",{"vendor_slug":123,"vendor_name":124,"vendor_logo":125,"product_slug":123,"product_name":126,"url":127,"description":128},"sosafe","SoSafe","\u002Fvendor-logos\u002Fsosafe.png","SoSafe Awareness Platform","https:\u002F\u002Fsosafe-awareness.com\u002F","Behaviour-based awareness training and phishing simulation in many languages.",[130],{"slug":131,"name":132,"logo_path":133,"roles":134},"check-point","Check Point","\u002Fvendor-logos\u002Fcheck-point.png",[135],"reported_by",{"slug":137,"title":138,"body":139,"framework_refs":140,"framework_notes":148},"chatgpt-lockdown-mode-bypass-exposed-chat-histories-and-credentials","ChatGPT Lockdown Mode Bypass Exposed Chat Histories and Credentials","Check Point Research uncovered a vulnerability in ChatGPT's Lockdown Mode that fundamentally undermined a security feature users trusted to protect their data. Attackers could exploit this flaw to silently exfiltrate entire conversation histories, serve convincing fake update prompts to deliver malware, and harvest login credentials — all without the user's knowledge. The incident highlights a dangerous gap between perceived security (a named 'Lockdown Mode') and actual security guarantees. It matters because users placed elevated trust in a named security feature, amplifying the potential harm when that feature failed. OpenAI's subsequent patch demonstrates that even purpose-built security controls require rigorous, ongoing vulnerability testing.",[141,142,143,144,145,146,147],"CIS Control 7: Continuous Vulnerability Management","NIST SP 800-53 SI-2: Flaw Remediation","ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities","GDPR Article 32","MITRE ATT&CK T1566: Phishing","OWASP A06:2021 Vulnerable and Outdated Components","CIS Control 14: Security Awareness and Skills Training",{"GDPR Article 32":149,"MITRE ATT&CK T1566: Phishing":150,"NIST SP 800-53 SI-2: Flaw Remediation":151,"OWASP A06:2021 Vulnerable and Outdated Components":152,"CIS Control 7: Continuous Vulnerability Management":153,"CIS Control 14: Security Awareness and Skills Training":154,"ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities":155},"GDPR Article 32 requires appropriate technical measures to ensure data security; exploiting this flaw to exfiltrate chat histories containing personal data constitutes a failure of that obligation.","The fake update window used in this attack is a classic in-application phishing technique designed to trick users into downloading malware, directly mapped to this ATT&CK technique.","SI-2 requires organizations to identify, report, and correct information system flaws; applying this to third-party AI tools would mandate timely patching once OpenAI released the fix.","Relying on an unpatched version of ChatGPT with a known security bypass falls squarely under the risk of using vulnerable components that expose users to data theft and malware delivery.","Regular vulnerability scanning and a structured patching cadence would have identified and remediated the ChatGPT Lockdown Mode flaw before attackers could exploit it to steal conversations.","Users who understand social engineering tactics would be less likely to fall for fake update prompts served through the compromised Lockdown Mode interface, limiting the attack's malware delivery phase.","This control requires timely identification and remediation of technical vulnerabilities in information systems, which would apply to externally hosted AI platforms handling organizational data."]