[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f8DTnV2WPdP6HkztKamJeprLGbakgNALK1w_-3H9zBQc":3},{"article":4,"iocs":47,"watch_terms":48,"solutions":49,"lesson":77},{"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},"89b78841-b723-4973-9e17-1a164ef4f43a","Users in Houthi-Held Yemen Tried to Develop Advanced Weapons With AI, Anthropic Says","users-in-houthi-held-yemen-tried-to-develop-advanced-weapons-with-ai-anthropic-s-d89ce8","Anthropic said the users did not succeed in “fielding an operational device” but did carry out a failed test of a guided rocket. The post Users in Houthi-Held Yemen Tried to Develop Advanced Weapons With AI, Anthropic Says appeared first on SecurityWeek.","Anthropic has identified users in Houthi-controlled Yemen who attempted to leverage its Claude AI chatbot to develop advanced weapons systems, including hypersonic missiles and maneuverable warheads. While the users did not succeed in fielding an operational device and even returned to the chatbot to troubleshoot a failed guided rocket test, the effort highlights the growing use of AI in warfare and raises concerns about its proliferation.","Houthi-aligned users in Yemen attempted to develop advanced weapons using Anthropic's AI.","https:\u002F\u002Fwww.securityweek.com\u002Fusers-in-houthi-held-yemen-tried-to-develop-advanced-weapons-with-ai-anthropic-says\u002F","https:\u002F\u002Fwww.securityweek.com\u002Fwp-content\u002Fuploads\u002F2023\u002F01\u002FThreat_Intelligence.jpg","2026-09-12T01:50:53+00:00","2026-09-12T02:00:08.136774+00:00",8,[17,20,23,26],{"name":18,"type":19},"Houthis","threat_actor",{"name":21,"type":22},"Anthropic","vendor",{"name":24,"type":25},"Claude","product",{"name":27,"type":28},"AI","technology","6cbdd207-aaa1-4176-9534-e156b125e917",{"id":29,"icon":31,"name":32,"slug":33},null,"Nation-state","nation-state",[35,37,42],{"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},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[],[21,24],{"controls":50,"vendors":76},[51],{"slug":41,"name":52,"problem":53,"products":54},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[55,63,71],{"vendor_slug":56,"vendor_name":57,"vendor_logo":58,"product_slug":59,"product_name":60,"url":61,"description":62},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","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.",{"vendor_slug":64,"vendor_name":65,"vendor_logo":66,"product_slug":67,"product_name":68,"url":69,"description":70},"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":56,"vendor_name":57,"vendor_logo":58,"product_slug":72,"product_name":73,"url":74,"description":75},"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.",[],{"slug":78,"title":79,"body":80,"framework_refs":81,"framework_notes":92},"ai-chatbot-misuse-houthi-users-attempted-weapons-development-via-claude","AI Chatbot Misuse: Houthi Users Attempted Weapons Development via Claude","Anthropic identified users in Houthi-controlled Yemen attempting to weaponize its Claude AI platform to design hypersonic missiles and guided warheads, exploiting the accessibility of commercial AI tools for military R&D purposes. This incident underscores a critical gap in AI platform governance: general-purpose AI systems can be queried for highly sensitive, dual-use technical knowledge without sufficient guardrails. The fact that users returned to the chatbot to troubleshoot a failed rocket test reveals that AI is being embedded into active weapons development cycles, not merely theoretical exploration. This matters because AI proliferation is outpacing the regulatory and technical controls needed to prevent nation-state and non-state actors from extracting dangerous capabilities at scale.",[82,83,84,85,86,87,88,89,90,91],"NIST AI RMF – GOVERN 1.1 (Policies for AI risk management)","NIST AI RMF – MAP 2.3 (Identification of dual-use risks)","CIS Control 3: Data Protection (restrict sensitive output generation)","CIS Control 13: Network Monitoring and Defense (monitor AI query patterns)","NIST SP 800-53 AC-2 (Account Management and access restrictions)","NIST SP 800-53 SI-10 (Information Input Validation)","EU AI Act – Article 5 (Prohibited AI practices including weapons facilitation)","OFAC Sanctions Compliance Framework (geographic access controls)","Export Administration Regulations (EAR) – Dual-Use Technology Controls","ISO\u002FIEC 42001 – AI Management System (responsible AI governance)",{}]