[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fJf4T1rOlYkodPdFnjvais4Qu34Z5aiqAt6qHXzwaaz4":3},{"article":4,"iocs":49,"watch_terms":50,"solutions":51,"lesson":139},{"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":33,"category":34,"article_tags":38},"bd25908b-1612-4027-9220-4a3eb43f23c5","ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link","chatgpt-agentforger-flaw-could-deploy-rogue-workspace-agents-via-a-phishing-link-d43d2a","Cybersecurity researchers have disclosed a critical vulnerability in OpenAI's ChatGPT Workspace Agents that could have allowed a single phishing link to stealthily build, authorize, and deploy an autonomous artificial intelligence (AI) agent inside a victim's organization. The vulnerability has been codenamed AgentForger by Zenity Labs. The issue has since been addressed by OpenAI as of June 8,","Zenity Labs disclosed a critical CSRF vulnerability in OpenAI's ChatGPT Workspace Agents (codenamed AgentForger) that could allow attackers to deploy malicious autonomous AI agents within victim organizations through a single phishing link. The flaw exploited URL parameter injection to automatically create and authorize agents with access to enterprise connectors like Outlook, Gmail, and Slack without user approval. OpenAI patched the vulnerability on June 8, 2026, and announced deprecation of Agent Builder in favor of the Agents SDK.","ChatGPT AgentForger CSRF flaw allows deploying rogue workspace agents via phishing links.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F07\u002Fchatgpt-agentforger-flaw-could-deploy.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEiWjz4Sgp8xNXyO8juw5bycoRamRay35GLzSBPG3I3UWyuUovp8-qM8hMgxWiqIwW45q1cb17EkWhEYmP8ODPyhUTk1j7P2T92fjAW_R1WKleVJsywM7kzongXurU8N9olKf1F1jxpDnBKvY0s2F_wsgoGWYgRFrzN5zAoQZciTWQjLQw5NJRL66s3S1RaT\u002Fs1600\u002Fchatgpt.jpg","2026-07-24T11:53:55+00:00","2026-07-24T14:00:23.468841+00:00",9,[17,20,23,25,28,30],{"name":18,"type":19},"OpenAI","vendor",{"name":21,"type":22},"ChatGPT Workspace Agents","product",{"name":24,"type":22},"Agent Builder",{"name":26,"type":27},"Agents SDK","technology",{"name":29,"type":19},"Zenity Labs",{"name":31,"type":32},"AgentForger","campaign","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":33,"icon":35,"name":36,"slug":37},null,"Vulnerabilities","vulnerabilities",[39,44],{"category":40},{"id":41,"icon":35,"name":42,"slug":43},"2c8f44d4-b56e-47cf-9677-04f22c9ee78d","Identity & Access","identity-access",{"category":45},{"id":46,"icon":35,"name":47,"slug":48},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",[],[18,29,21],{"controls":52,"vendors":138},[53,82,111],{"slug":54,"name":55,"problem":56,"products":57},"phishing-resistant-mfa","Phishing-resistant MFA","A stolen password, or a user who taps Approve on a push prompt, is no longer enough to log in.",[58,66,74],{"vendor_slug":59,"vendor_name":60,"vendor_logo":61,"product_slug":62,"product_name":63,"url":64,"description":65},"okta","Okta","\u002Fvendor-logos\u002Fokta.png","workforce-identity","Okta Workforce Identity","https:\u002F\u002Fwww.okta.com\u002Fproducts\u002Fworkforce-identity\u002F","Single sign-on, adaptive MFA including phishing-resistant methods, and lifecycle management for employees.",{"vendor_slug":67,"vendor_name":68,"vendor_logo":69,"product_slug":70,"product_name":71,"url":72,"description":73},"yubico","Yubico","\u002Fvendor-logos\u002Fyubico.png","yubikey","YubiKey","https:\u002F\u002Fwww.yubico.com\u002Fproducts\u002F","Hardware security keys for FIDO2, passkeys and smart card login, in USB and NFC versions.",{"vendor_slug":75,"vendor_name":76,"vendor_logo":77,"product_slug":78,"product_name":79,"url":80,"description":81},"cisco","Cisco","\u002Fvendor-logos\u002Fcisco.png","duo","Cisco Duo","https:\u002F\u002Fduo.com\u002F","MFA and device trust, with support for passkeys and security keys.",{"slug":83,"name":84,"problem":85,"products":86},"email-security","Email security","Phishing, malware and invoice fraud are filtered out before they reach inboxes.",[87,95,103],{"vendor_slug":88,"vendor_name":89,"vendor_logo":90,"product_slug":91,"product_name":92,"url":93,"description":94},"check-point","Check Point","\u002Fvendor-logos\u002Fcheck-point.png","harmony-email","Harmony Email & Collaboration","https:\u002F\u002Fwww.checkpoint.com\u002Fharmony\u002Femail-security\u002F","Email and collaboration security for Microsoft 365 and Google Workspace.",{"vendor_slug":96,"vendor_name":97,"vendor_logo":98,"product_slug":99,"product_name":100,"url":101,"description":102},"mimecast","Mimecast","\u002Fvendor-logos\u002Fmimecast.png","mimecast-email-security","Mimecast Email Security","https:\u002F\u002Fwww.mimecast.com\u002Fproducts\u002Femail-security\u002F","Email filtering, impersonation protection and continuity.",{"vendor_slug":104,"vendor_name":105,"vendor_logo":106,"product_slug":107,"product_name":108,"url":109,"description":110},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","defender-for-office-365","Microsoft Defender for Office 365","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fsiem-and-xdr\u002Fmicrosoft-defender-office-365","Protection for Exchange Online, Teams and SharePoint against phishing, malicious links and attachments.",{"slug":112,"name":113,"problem":114,"products":115},"security-awareness-training","Security awareness training and phishing simulation","People recognise and report attacks instead of falling for them.",[116,123,130],{"vendor_slug":117,"vendor_name":118,"vendor_logo":119,"product_slug":117,"product_name":120,"url":121,"description":122},"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":124,"vendor_name":125,"vendor_logo":126,"product_slug":112,"product_name":127,"url":128,"description":129},"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.",{"vendor_slug":131,"vendor_name":132,"vendor_logo":133,"product_slug":134,"product_name":135,"url":136,"description":137},"huntress","Huntress","\u002Fvendor-logos\u002Fhuntress.png","managed-sat","Huntress Managed Security Awareness Training","https:\u002F\u002Fwww.huntress.com\u002Fplatform\u002Fsecurity-awareness-training","Security awareness training and phishing simulation, managed for you.",[],{"slug":140,"title":141,"body":142,"framework_refs":143,"framework_notes":157},"chatgpt-agentforger-csrf-flaw-enabled-rogue-ai-agent-deployment-via-phishing","ChatGPT AgentForger CSRF Flaw Enabled Rogue AI Agent Deployment via Phishing","A critical Cross-Site Request Forgery (CSRF) vulnerability in OpenAI's ChatGPT Workspace Agents allowed attackers to deploy unauthorized autonomous AI agents within enterprise environments simply by tricking a user into clicking a phishing link. The flaw leveraged URL parameter injection to bypass user approval workflows, granting rogue agents access to sensitive enterprise connectors such as Outlook, Gmail, and Slack — all without the victim's explicit consent. This is particularly dangerous because AI agents can autonomously take actions at scale, meaning a single successful phishing click could result in mass data exfiltration, lateral movement, or manipulation of business communications. The incident highlights how rapidly expanding AI tooling introduces novel attack surfaces that traditional security controls are not yet designed to address.",[144,145,146,147,148,149,150,151,152,153,154,155,156],"CIS Control 4: Secure Configuration of Enterprise Assets and Software","CIS Control 6: Access Control Management","CIS Control 7: Continuous Vulnerability Management","CIS Control 14: Security Awareness and Skills Training","NIST SP 800-53 AC-2: Account Management","NIST SP 800-53 AC-6: Least Privilege","NIST SP 800-53 SC-8: Transmission Confidentiality and Integrity","NIST SP 800-53 SI-2: Flaw Remediation","NIST SP 800-53 IA-8: Identification and Authentication (Non-Organizational Users)","NIST CSF ID.AM-2: Software platforms and applications inventoried","GDPR Article 32: Security of Processing (for EU organizations exposing personal data via compromised connectors)","OWASP CSRF Prevention Cheat Sheet","ITIL Change Management: Emergency Change procedures for critical security patches",{}]