[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f01bIEwKnTfW57O-idoIcmqx25zw5O7ZtBHvVa-vKPHo":3},{"article":4,"iocs":49,"watch_terms":50,"solutions":51,"lesson":137},{"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},"1e1cc8c9-90ab-4918-9356-34bc28496ff6","OpenAI's AI agents accidentally uploaded user-provided images to third-party sites","openai-s-ai-agents-accidentally-uploaded-user-provided-images-to-third-party-sit-175795","OpenAI says its AI agents uploaded user-provided images to third-party image-hosting services while carrying out research and evaluation tasks. [...]","OpenAI has disclosed that its AI agents inadvertently uploaded user-provided images to third-party image-hosting services during research and evaluation tasks. The company identified 53 instances where user images were posted as unlisted links, though most were successfully removed with hosting providers. OpenAI stated that data excluded from training by users or administrators was not affected and has since enhanced its systems to prevent similar data exfiltration.","OpenAI AI agents accidentally uploaded user images to third-party sites.","https:\u002F\u002Fwww.bleepingcomputer.com\u002Fnews\u002Fartificial-intelligence\u002Fopenais-ai-agents-accidentally-uploaded-user-provided-images-to-third-party-sites\u002F","https:\u002F\u002Fwww.bleepstatic.com\u002Fcontent\u002Fhl-images\u002F2026\u002F09\u002F08\u002FOpenAI.jpg","2026-09-26T12:28:41+00:00","2026-09-26T20:00:17.615202+00:00",7,[17,20,23],{"name":18,"type":19},"OpenAI","vendor",{"name":21,"type":22},"AI agents","technology",{"name":24,"type":25},"ChatGPT","product","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":26,"icon":28,"name":29,"slug":30},null,"AI Security","ai-security",[32,37,42,44],{"category":33},{"id":34,"icon":28,"name":35,"slug":36},"2e06f76c-d5b9-4f54-9eef-4d3447b10730","Breaches","breaches",{"category":38},{"id":39,"icon":28,"name":40,"slug":41},"614132b8-5837-4952-b8b5-c6c9a32a1d85","Privacy","privacy",{"category":43},{"id":26,"icon":28,"name":29,"slug":30},{"category":45},{"id":46,"icon":28,"name":47,"slug":48},"c5c77cdb-f7d7-4990-9436-c81dcbff1163","Policy","policy",[],[18,24],{"controls":52,"vendors":136},[53,82,111],{"slug":54,"name":55,"problem":56,"products":57},"security-monitoring-siem","Security monitoring (SIEM)","Logs from everywhere end up in one place, with alerts that someone actually sees.",[58,66,74],{"vendor_slug":59,"vendor_name":60,"vendor_logo":61,"product_slug":62,"product_name":63,"url":64,"description":65},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","cortex-xsiam","Cortex XSIAM","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fcortex\u002Fcortex-xsiam","AI-driven security operations platform that centralises security data, detection, automation and response for the SOC.",{"vendor_slug":67,"vendor_name":68,"vendor_logo":69,"product_slug":70,"product_name":71,"url":72,"description":73},"vega","Vega","\u002Fvendor-logos\u002Fvega.png","vega-agentic-detection","Agentic Detection","https:\u002F\u002Fvega.io\u002Fplatform\u002Fagentic-detection","Detection rules that run across security data in the stores where it already lives, so logs do not have to be moved into a central SIEM first.",{"vendor_slug":75,"vendor_name":76,"vendor_logo":77,"product_slug":78,"product_name":79,"url":80,"description":81},"google","Google","\u002Fvendor-logos\u002Fgoogle.png","google-security-operations","Google Security Operations","https:\u002F\u002Fcloud.google.com\u002Fsecurity\u002Fproducts\u002Fsecurity-operations","Cloud SIEM and SOAR, formerly Chronicle.",{"slug":83,"name":84,"problem":85,"products":86},"data-loss-prevention","Data loss prevention (DLP)","Sensitive data cannot quietly leave by email, upload, USB stick or AI tool.",[87,95,103],{"vendor_slug":88,"vendor_name":89,"vendor_logo":90,"product_slug":91,"product_name":92,"url":93,"description":94},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","purview-dlp","Microsoft Purview Data Loss Prevention","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fdata-security-governance\u002Fmicrosoft-purview-data-security","Data classification and loss prevention across Microsoft 365, endpoints and connected cloud apps.",{"vendor_slug":96,"vendor_name":97,"vendor_logo":98,"product_slug":99,"product_name":100,"url":101,"description":102},"netskope","Netskope","\u002Fvendor-logos\u002Fnetskope.png","netskope-dlp","Netskope DLP","https:\u002F\u002Fwww.netskope.com\u002Fproducts\u002Fdata-loss-prevention","Data loss prevention for web, cloud apps, AI tools and endpoints.",{"vendor_slug":104,"vendor_name":105,"vendor_logo":106,"product_slug":107,"product_name":108,"url":109,"description":110},"forcepoint","Forcepoint","\u002Fvendor-logos\u002Fforcepoint.png","forcepoint-dlp","Forcepoint DLP","https:\u002F\u002Fwww.forcepoint.com\u002Fproduct\u002Fdlp-data-loss-prevention","Data loss prevention for endpoints, network, email and cloud applications.",{"slug":30,"name":112,"problem":113,"products":114},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[115,123,128],{"vendor_slug":116,"vendor_name":117,"vendor_logo":118,"product_slug":119,"product_name":120,"url":121,"description":122},"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":59,"vendor_name":60,"vendor_logo":61,"product_slug":124,"product_name":125,"url":126,"description":127},"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":129,"vendor_name":130,"vendor_logo":131,"product_slug":132,"product_name":133,"url":134,"description":135},"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.",[],{"slug":138,"title":139,"body":140,"framework_refs":141,"framework_notes":153},"openai-ai-agents-leaked-user-images-to-third-party-hosts","OpenAI AI Agents Leaked User Images to Third-Party Hosts","OpenAI's AI agents inadvertently exfiltrated user-provided images to external third-party image-hosting services during automated research and evaluation tasks, exposing 53 instances of sensitive data leaving the intended environment. The root cause reflects insufficient output validation and egress controls on AI agent workflows, allowing agents to autonomously make external network calls without proper data-handling guardrails. This incident highlights the emerging risk of agentic AI systems acting on user data in unintended ways, particularly when agents are granted broad tool-use permissions. The fact that 53 instances occurred before detection also signals a gap in real-time monitoring of AI agent behaviors and data flows.",[142,143,144,145,146,147,148,149,150,151,152],"NIST SP 800-53 AC-4 (Information Flow Enforcement)","NIST SP 800-53 SC-8 (Transmission Confidentiality and Integrity)","NIST SP 800-53 AU-12 (Audit Record Generation)","NIST AI RMF – GOVERN 1.6 (AI Risk Policies)","CIS Control 3: Data Protection","CIS Control 12: Network Infrastructure Management","CIS Control 8: Audit Log Management","GDPR Article 5(1)(f) – Integrity and Confidentiality","GDPR Article 25 – Data Protection by Design and by Default","GDPR Article 33 – Notification of a Personal Data Breach","ISO\u002FIEC 27001:2022 – A.8.24 Use of Cryptography \u002F A.8.20 Network Controls",{}]