[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fQieg0nJuUv67AT4z2RhkihODxbgumvp80f-1bnzkY4g":3},{"article":4,"iocs":55,"watch_terms":69,"solutions":70,"lesson":158},{"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":32,"category":33,"article_tags":37},"12f4d514-ead7-4f61-b605-0732de583625","ARTEX goes from pentesting tool to attacker staple in three months","artex-goes-from-pentesting-tool-to-attacker-staple-in-three-months-3d19a4","A security researcher’s AI agent breached an internal sales application used by WorkOS’s go-to-market teams, the developer platform provider confirmed on Friday. “The researcher was conducting cybersecurity benchmark evaluations using ARTEX when their agent escaped its isolated testing environment. Its interaction with WorkOS was unintended,” WorkOS said. The researcher confirmed that they deleted and did not further share the customer data the agent obtained from WorkOS’s systems, and the company acknowledged the security failings that … More → The post ARTEX goes from pentesting tool to attacker staple in three months appeared first on Help Net Security.","The open-source AI penetration testing framework ARTEX, released in July 2026, has been quickly adopted by various threat actors, including financially motivated groups and state-sponsored entities. Attackers are using ARTEX agents to automate tasks like credential theft, data exfiltration, and breaching cloud tenants, with some operations occurring at machine speed. This rapid weaponization highlights a broader trend of threat actors leveraging AI-powered offensive frameworks for scaled intrusions.","AI pentesting tool ARTEX rapidly weaponized by threat actors for data theft and espionage.","https:\u002F\u002Fwww.helpnetsecurity.com\u002F2026\u002F11\u002F09\u002Fartex-goes-from-pentesting-tool-to-attacker-staple-in-three-months\u002F","https:\u002F\u002Fimg.helpnetsecurity.com\u002Fwp-content\u002Fuploads\u002F2023\u002F11\u002F30082950\u002Fartificial_intelligence-1.jpg","2026-11-09T14:57:32+00:00","2026-11-09T16:00:23.536911+00:00",9,[17,20,23,25,27,29],{"name":18,"type":19},"ARTEX","product",{"name":21,"type":22},"WorkOS","vendor",{"name":24,"type":22},"CrowdStrike",{"name":26,"type":22},"Microsoft",{"name":28,"type":22},"Google",{"name":30,"type":31},"Storm-0940","threat_actor","e7b231c8-5f79-4465-8d38-1ef13aea5a14",{"id":32,"icon":34,"name":35,"slug":36},null,"Threat Intelligence","threat-intelligence",[38,43,48,53],{"category":39},{"id":40,"icon":34,"name":41,"slug":42},"02371804-cf6d-4449-98de-f1a2d4d9b266","Tools","tools",{"category":44},{"id":45,"icon":34,"name":46,"slug":47},"26b0b636-0e31-4db1-bffb-61bdf9f20a58","Supply Chain","supply-chain",{"category":49},{"id":50,"icon":34,"name":51,"slug":52},"6cbdd207-aaa1-4176-9534-e156b125e917","Nation-state","nation-state",{"category":54},{"id":32,"icon":34,"name":35,"slug":36},[56,59,62,65,67],{"type":57,"value":18,"context":58},"malware","AI-driven open-source penetration testing framework weaponized by threat actors.",{"type":57,"value":60,"context":61},"ScopeWeaver","Rebranded version of ARTEX.",{"type":57,"value":63,"context":64},"PentAGI","Similar AI agentic offensive intrusion framework.",{"type":57,"value":66,"context":64},"Hexstrike",{"type":57,"value":68,"context":64},"CAIRN",[24,26,28],{"controls":71,"vendors":148},[72,99,122],{"slug":73,"name":74,"problem":75,"products":76},"identity-threat-detection","Identity threat detection and response (ITDR)","Attackers who log in with real, stolen credentials get noticed.",[77,84,92],{"vendor_slug":78,"vendor_name":24,"vendor_logo":79,"product_slug":80,"product_name":81,"url":82,"description":83},"crowdstrike","\u002Fvendor-logos\u002Fcrowdstrike.png","falcon-identity-protection","Falcon Identity Protection","https:\u002F\u002Fwww.crowdstrike.com\u002Fen-us\u002Fplatform\u002Fnext-gen-identity-security\u002Fidentity-protection\u002F","Detection of identity attacks against Active Directory and Entra ID, with risk-based MFA.",{"vendor_slug":85,"vendor_name":86,"vendor_logo":87,"product_slug":88,"product_name":89,"url":90,"description":91},"vectra-ai","Vectra AI","\u002Fvendor-logos\u002Fvectra-ai.png","vectra-ai-platform","Vectra AI Platform","https:\u002F\u002Fwww.vectra.ai\u002Fplatform","Detection of attacker behaviour across network, identity and cloud.",{"vendor_slug":93,"vendor_name":26,"vendor_logo":94,"product_slug":95,"product_name":96,"url":97,"description":98},"microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","defender-for-identity","Microsoft Defender for Identity","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fsiem-and-xdr\u002Fmicrosoft-defender-for-identity","Detects attacks against on-premises Active Directory and hybrid identities.",{"slug":100,"name":101,"problem":102,"products":103},"endpoint-detection-response","Endpoint detection and response (EDR and XDR)","Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.",[104,109,117],{"vendor_slug":78,"vendor_name":24,"vendor_logo":79,"product_slug":105,"product_name":106,"url":107,"description":108},"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":110,"vendor_name":111,"vendor_logo":112,"product_slug":113,"product_name":114,"url":115,"description":116},"elastic","Elastic","\u002Fvendor-logos\u002Felastic.png","elastic-security","Elastic Security","https:\u002F\u002Fwww.elastic.co\u002Fsecurity","SIEM and endpoint security built on Elasticsearch, with open detection rules.",{"vendor_slug":93,"vendor_name":26,"vendor_logo":94,"product_slug":118,"product_name":119,"url":120,"description":121},"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.",{"slug":123,"name":124,"problem":125,"products":126},"ai-security","AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[127,135,143],{"vendor_slug":128,"vendor_name":129,"vendor_logo":130,"product_slug":131,"product_name":132,"url":133,"description":134},"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":136,"vendor_name":137,"vendor_logo":138,"product_slug":139,"product_name":140,"url":141,"description":142},"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":128,"vendor_name":129,"vendor_logo":130,"product_slug":144,"product_name":145,"url":146,"description":147},"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.",[149,152,156],{"slug":78,"name":24,"logo_path":79,"roles":150},[151],"reported_by",{"slug":153,"name":28,"logo_path":154,"roles":155},"google","\u002Fvendor-logos\u002Fgoogle.png",[151],{"slug":93,"name":26,"logo_path":94,"roles":157},[151],{"slug":159,"title":160,"body":161,"framework_refs":162,"framework_notes":170},"ai-pentesting-tool-artex-weaponized-by-threat-actors-within-months-of-release","AI Pentesting Tool ARTEX Weaponized by Threat Actors Within Months of Release","The open-source AI framework ARTEX was released as a legitimate penetration testing tool in July 2026 but was rapidly adopted by both financially motivated and state-sponsored threat actors within three months. Attackers leveraged its AI-powered agents to automate credential theft, data exfiltration, and cloud tenant breaches at machine speed, dramatically lowering the skill barrier for sophisticated intrusions. This case illustrates the dual-use danger of publicly releasing powerful offensive AI tooling without adequate safeguards or responsible disclosure frameworks. The speed of weaponization outpaced the ability of most organizations to detect and respond to novel AI-driven attack patterns, underscoring how the threat landscape can shift nearly overnight when capable tools become freely available.",[163,164,165,166,167,168,169],"MITRE ATT&CK T1566: Phishing","CIS Control 17: Incident Response Management","CIS Control 14: Security Awareness and Skills Training","NIST CSF 2.0 PR.AA: Identity Management, Authentication, and Access Control","NIST SP 800-53 SI-2: Flaw Remediation","ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities","NIS2 Article 21(2)(b)",{"NIS2 Article 21(2)(b)":171,"MITRE ATT&CK T1566: Phishing":172,"NIST SP 800-53 SI-2: Flaw Remediation":173,"CIS Control 17: Incident Response Management":174,"CIS Control 14: Security Awareness and Skills Training":175,"ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities":176,"NIST CSF 2.0 PR.AA: Identity Management, Authentication, and Access Control":177},"NIS2 requires incident handling and monitoring capabilities proportionate to emerging threats; the AI-speed operations of ARTEX demand exactly the kind of advanced detection and response posture this article mandates for critical entities.","ARTEX agents automate initial access techniques including credential harvesting; mapping attacker TTPs to ATT&CK allows defenders to build detections for each stage of the AI-driven kill chain before it completes.","Organizations relying on unpatched or misconfigured systems provided easy footholds for ARTEX agents; systematic flaw remediation processes would have reduced the exploitable attack surface.","The machine-speed nature of ARTEX-driven attacks demands pre-built, rehearsed incident response playbooks specifically designed for automated intrusions, which CIS Control 17 mandates organizations develop and test.","Security teams were largely unprepared for AI-powered offensive tooling; structured awareness and skills training would ensure analysts recognize and respond to AI-driven attack patterns as they emerge.","The rapid weaponization of ARTEX exploited organizations that lacked continuous vulnerability tracking; this control requires timely identification and treatment of technical vulnerabilities before attackers act on them.","ARTEX's automated credential theft succeeded in breaching cloud tenants, highlighting the need for strong identity controls and MFA that this framework element requires to limit unauthorized access."]