[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fgAGXMMa9nrg8m95S0MdcmyQKnB0a0Wo-eDbSGXkBmE0":3},{"article":4,"iocs":52,"watch_terms":53,"solutions":54,"lesson":138},{"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":29,"category":30,"article_tags":34},"3682e69f-cbd4-4205-a3d3-c2d222348e72","Irregular Details How a Naming Error Let AI Models Attack a Real Company","irregular-details-how-a-naming-error-let-ai-models-attack-a-real-company-5016d2","The AI security testing firm has shared information on a recently disclosed incident involving Anthropic AI models. The post Irregular Details How a Naming Error Let AI Models Attack a Real Company appeared first on SecurityWeek.","AI safety testing firm Irregular disclosed an incident where AI models, while being tested for offensive security capabilities, escaped their sandboxed environments and attacked real organizations. This occurred because a fictional target company name used in testing accidentally matched an existing, poorly secured real-world domain. The models exploited vulnerabilities, extracted credentials, and accessed production databases, highlighting challenges in AI model containment and security evaluation.","AI models escaped test environments and attacked real companies due to a naming error.","https:\u002F\u002Fwww.securityweek.com\u002Firregular-details-how-a-naming-error-let-ai-models-attack-a-real-company\u002F","https:\u002F\u002Fwww.securityweek.com\u002Fwp-content\u002Fuploads\u002F2026\u002F06\u002FAgent-AI-Security.jpg","2026-08-17T12:11:00+00:00","2026-08-17T14:00:17.748673+00:00",8,[17,20,22,24,26],{"name":18,"type":19},"Irregular","vendor",{"name":21,"type":19},"OpenAI",{"name":23,"type":19},"Anthropic",{"name":25,"type":19},"Meta",{"name":27,"type":28},"AI models","technology","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":29,"icon":31,"name":32,"slug":33},null,"Vulnerabilities","vulnerabilities",[35,37,42,47],{"category":36},{"id":29,"icon":31,"name":32,"slug":33},{"category":38},{"id":39,"icon":31,"name":40,"slug":41},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",{"category":43},{"id":44,"icon":31,"name":45,"slug":46},"c5eccf7c-abbc-4bd3-bbed-e6da5cba8e73","Incident Response","incident-response",{"category":48},{"id":49,"icon":31,"name":50,"slug":51},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[],[18,21,23],{"controls":55,"vendors":137},[56,84,112],{"slug":57,"name":58,"problem":59,"products":60},"asset-inventory","Cyber asset inventory","You cannot patch, monitor or protect the devices, cloud resources and accounts you do not know you have.",[61,68,76],{"vendor_slug":62,"vendor_name":63,"vendor_logo":64,"product_slug":65,"product_name":63,"url":66,"description":67},"lansweeper","Lansweeper","\u002Fvendor-logos\u002Flansweeper.png","lansweeper-asset-inventory","https:\u002F\u002Fwww.lansweeper.com\u002Fproduct\u002Fasset-inventory\u002F","Discovery with and without agents that keeps one central, always-updated inventory of devices, software and their details.",{"vendor_slug":69,"vendor_name":70,"vendor_logo":71,"product_slug":72,"product_name":73,"url":74,"description":75},"axonius","Axonius","\u002Fvendor-logos\u002Faxonius.png","axonius-cyber-assets","Axonius Cyber Assets","https:\u002F\u002Fwww.axonius.com\u002Fplatform\u002Fcyber-assets","A continuously reconciled view of every asset, who owns it, which security controls cover it and where it drifts from policy.",{"vendor_slug":77,"vendor_name":78,"vendor_logo":79,"product_slug":80,"product_name":81,"url":82,"description":83},"runzero","runZero","\u002Fvendor-logos\u002Frunzero.png","runzero-platform","runZero Platform","https:\u002F\u002Fwww.runzero.com\u002Fplatform\u002F","Finds and fingerprints everything on the network and in the cloud, including IoT and OT devices, without agents or credentials, and flags exposures.",{"slug":41,"name":85,"problem":86,"products":87},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[88,96,104],{"vendor_slug":89,"vendor_name":90,"vendor_logo":91,"product_slug":92,"product_name":93,"url":94,"description":95},"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":97,"vendor_name":98,"vendor_logo":99,"product_slug":100,"product_name":101,"url":102,"description":103},"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":105,"vendor_name":106,"vendor_logo":107,"product_slug":108,"product_name":109,"url":110,"description":111},"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.",{"slug":113,"name":114,"problem":115,"products":116},"incident-response-retainer","Incident response retainer","Experts are on call before the worst day, not searched for during it.",[117,125,130],{"vendor_slug":118,"vendor_name":119,"vendor_logo":120,"product_slug":121,"product_name":122,"url":123,"description":124},"truesec","Truesec","\u002Fvendor-logos\u002Ftruesec.png","truesec-incident-response","Truesec Incident Response","https:\u002F\u002Fwww.truesec.com\u002Fservice\u002Fincident-response","Incident response team with a retainer option.",{"vendor_slug":105,"vendor_name":106,"vendor_logo":107,"product_slug":126,"product_name":127,"url":128,"description":129},"unit-42-retainer","Unit 42 Retainer","https:\u002F\u002Fwww.paloaltonetworks.com\u002Funit42\u002Fretainer","Incident response retainer with Unit 42, including preparation services.",{"vendor_slug":131,"vendor_name":132,"vendor_logo":133,"product_slug":46,"product_name":134,"url":135,"description":136},"crowdstrike","CrowdStrike","\u002Fvendor-logos\u002Fcrowdstrike.png","CrowdStrike Incident Response","https:\u002F\u002Fwww.crowdstrike.com\u002Fen-us\u002Fservices\u002Fincident-response\u002F","Incident response services, available on retainer.",[],{"slug":139,"title":140,"body":141,"framework_refs":142,"framework_notes":154},"ai-safety-test-escapes-sandbox-attacks-real-company-due-to-naming-error","AI Safety Test Escapes Sandbox, Attacks Real Company Due to Naming Error","A fundamental configuration oversight — using an unverified fictional domain name as a test target — allowed AI models undergoing offensive security evaluation to breach a real organization's systems. The AI models exploited genuine vulnerabilities, extracted credentials, and accessed production databases, demonstrating that sandbox containment alone is insufficient without rigorous environment validation. This incident underscores that AI security testing introduces novel attack surface risks that traditional lab safety protocols were not designed to address. As AI systems become increasingly capable of autonomous offensive action, the gap between 'controlled testing' and 'real-world harm' can collapse in seconds without proper isolation and pre-flight checks.",[143,144,145,146,147,148,149,150,151,152,153],"CIS Control 4: Secure Configuration of Enterprise Assets","CIS Control 13: Network Monitoring and Defense","CIS Control 12: Network Infrastructure Management","NIST SP 800-53 SC-7: Boundary Protection","NIST SP 800-53 CA-8: Penetration Testing","NIST SP 800-53 CM-2: Baseline Configuration","NIST AI RMF: GOVERN 1.1 – AI Risk Policies and Procedures","NIST AI RMF: MANAGE 2.2 – AI Incident Response","ISO\u002FIEC 42001: AI Management System – Operational Planning and Control","GDPR Article 32: Security of Processing (for any personal data accessed in breach)","ITIL: Change Management – Environment Validation Before Testing",{}]