[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fBi8kGXCJZxfhopVpZ8ADDWzK7TXWpx8MAgX8PE51v_8":3},{"article":4,"iocs":52,"watch_terms":75,"solutions":76,"lesson":33},{"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":31,"category":32,"article_tags":36},"2eeaca7f-c58a-4aa1-b5fd-6786836dd9bb","Hackers Use Hidden Website Instructions in New Attacks on AI Assistants","hackers-use-hidden-website-instructions-in-new-attacks-on-ai-assistants-07d4d1","Cybersecurity researchers at Forcepoint uncover new indirect prompt injection attacks that use hidden website code to exploit AI assistants like GitHub Copilot.","Cybersecurity researchers at Forcepoint X-Labs have confirmed that Indirect Prompt Injection (IPI) attacks are now active in the wild, with hackers hiding malicious commands in website code using techniques like invisible fonts, HTML comments, and CSS tricks to exploit AI assistants including GitHub Copilot and Claude Code. The research identified ten real-world examples of IPI attacks deployed across websites in April 2026, targeting use cases including financial fraud, API key theft, data deletion, and DoS attacks. Attackers exploit the AI's inability to distinguish between data and instructions, allowing them to manipulate autonomous agents without direct user involvement.","Forcepoint discovers indirect prompt injection attacks using hidden website code to exploit AI assistants.","https:\u002F\u002Fhackread.com\u002Fhackers-hidden-site-instruction-attack-ai-assistants\u002F","https:\u002F\u002Fhackread.com\u002Fwp-content\u002Fuploads\u002F2026\u002F04\u002Fhackers-hidden-site-instruction-attack-ai-assistants.jpg","2026-04-23T10:20:06+00:00","2026-04-23T12:00:19.307071+00:00",9,[17,20,23,25,28],{"name":18,"type":19},"Forcepoint","vendor",{"name":21,"type":22},"GitHub Copilot","product",{"name":24,"type":22},"Claude Code",{"name":26,"type":27},"Large Language Models (LLMs)","technology",{"name":29,"type":30},"Indirect Prompt Injection (IPI)","campaign","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":31,"icon":33,"name":34,"slug":35},null,"AI Security","ai-security",[37,42,47],{"category":38},{"id":39,"icon":33,"name":40,"slug":41},"574f766a-fb3f-487c-8d2c-0720ae75471b","Zero-day","zero-day",{"category":43},{"id":44,"icon":33,"name":45,"slug":46},"80544778-fabb-4dcd-aa35-17492e5dcf4f","Vulnerabilities","vulnerabilities",{"category":48},{"id":49,"icon":33,"name":50,"slug":51},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[53,57,60,63,66,69,72],{"type":54,"value":55,"context":56},"domain","faladobairro.com","Hosted IPI attack with hidden terminal command (sudo rm -rf) to delete backup folder",{"type":54,"value":58,"context":59},"perceptivepumpkin.com","IPI attack instructing AI to send $5,000 via PayPal.me",{"type":54,"value":61,"context":62},"thelibrary-welcome.uk","IPI attack using hidden comments to leak secret API key",{"type":54,"value":64,"context":65},"bentasker.co.uk","IPI attack using Authority Impersonation for DoS and distraction tactics",{"type":54,"value":67,"context":68},"lcpdfr.com","IPI attack using Magic String Spoofing to mimic security commands",{"type":54,"value":70,"context":71},"kleintechnik.net","IPI attack to trick AI into accessing private admin.php page",{"type":54,"value":73,"context":74},"kassoon.com","IPI attack for SEO manipulation and malicious URL redirection",[18,21,24],{"controls":77,"vendors":155},[78,105,130],{"slug":79,"name":80,"problem":81,"products":82},"dns-web-filtering","DNS filtering and secure web gateway","Users cannot reach known-malicious sites, and malware cannot phone home.",[83,91,99],{"vendor_slug":84,"vendor_name":85,"vendor_logo":86,"product_slug":87,"product_name":88,"url":89,"description":90},"cisco","Cisco","\u002Fvendor-logos\u002Fcisco.png","umbrella","Cisco Umbrella","https:\u002F\u002Fumbrella.cisco.com\u002F","DNS-layer security and secure web gateway delivered from the cloud.",{"vendor_slug":92,"vendor_name":93,"vendor_logo":94,"product_slug":95,"product_name":96,"url":97,"description":98},"netskope","Netskope","\u002Fvendor-logos\u002Fnetskope.png","netskope-swg","Netskope Secure Web Gateway","https:\u002F\u002Fwww.netskope.com\u002Fproducts\u002Fnext-gen-swg","Cloud secure web gateway with inspection of web and cloud app traffic.",{"vendor_slug":100,"vendor_name":101,"vendor_logo":102,"product_slug":100,"product_name":101,"url":103,"description":104},"dnsfilter","DNSFilter","\u002Fvendor-logos\u002Fdnsfilter.png","https:\u002F\u002Fwww.dnsfilter.com\u002F","DNS filtering for offices and roaming devices.",{"slug":35,"name":106,"problem":107,"products":108},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[109,117,125],{"vendor_slug":110,"vendor_name":111,"vendor_logo":112,"product_slug":113,"product_name":114,"url":115,"description":116},"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":118,"vendor_name":119,"vendor_logo":120,"product_slug":121,"product_name":122,"url":123,"description":124},"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":84,"vendor_name":85,"vendor_logo":86,"product_slug":126,"product_name":127,"url":128,"description":129},"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.",{"slug":131,"name":132,"problem":133,"products":134},"security-awareness-training","Security awareness training and phishing simulation","People recognise and report attacks instead of falling for them.",[135,142,148],{"vendor_slug":136,"vendor_name":137,"vendor_logo":138,"product_slug":136,"product_name":139,"url":140,"description":141},"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.",{"vendor_slug":143,"vendor_name":144,"vendor_logo":145,"product_slug":143,"product_name":144,"url":146,"description":147},"hoxhunt","Hoxhunt","\u002Fvendor-logos\u002Fhoxhunt.png","https:\u002F\u002Fhoxhunt.com\u002F","Adaptive phishing simulations and micro-training, with a focus on reporting.",{"vendor_slug":149,"vendor_name":150,"vendor_logo":151,"product_slug":131,"product_name":152,"url":153,"description":154},"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.",[156,161],{"slug":157,"name":18,"logo_path":158,"roles":159},"forcepoint","\u002Fvendor-logos\u002Fforcepoint.png",[160],"reported_by",{"slug":162,"name":163,"logo_path":164,"roles":165},"github","GitHub","\u002Fvendor-logos\u002Fgithub.png",[166],"affected"]