[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$ftOZoYoyCRtwRA4AVdeN0HB8NmW4wg0x2BYmPiPaybqM":3},{"article":4,"iocs":33,"watch_terms":34,"solutions":35,"lesson":63},{"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":20,"category":21,"article_tags":25},"2917144f-2bd1-4eb3-b925-bc73d0f96cc0","Agentic Browsers Rewind Web Security by 20 years","agentic-browsers-rewind-web-security-by-20-years-255566","PleaseFix class of flaws makes it easy to socially engineer agentic browsers and highlights weaknesses in how they handle cross-origin requests.","A new class of vulnerabilities, dubbed 'PleaseFix,' has been discovered in agentic browsers. These flaws make it easy to socially engineer these advanced browsers, exploiting weaknesses in how they manage cross-origin requests. This could potentially rewind web security practices back by two decades.","Agentic browsers face new 'PleaseFix' flaws impacting cross-origin request handling.","https:\u002F\u002Fwww.darkreading.com\u002Fendpoint-security\u002Fagentic-browsers-rewind-web-security-20-years","https:\u002F\u002Feu-images.contentstack.com\u002Fv3\u002Fassets\u002Fblt6d90778a997de1cd\u002Fbltf459c9ff5d345e58\u002F686d20d8a502a804ecf992c7\u002Fbrowser-security-Robert_Avgustin-shutterstock.jpg?width=720&quality=80&disable=upscale","2026-07-27T21:39:09+00:00","2026-07-28T12:00:05.994764+00:00",7,[17],{"name":18,"type":19},"agentic browsers","technology","80544778-fabb-4dcd-aa35-17492e5dcf4f",{"id":20,"icon":22,"name":23,"slug":24},null,"Vulnerabilities","vulnerabilities",[26,28],{"category":27},{"id":20,"icon":22,"name":23,"slug":24},{"category":29},{"id":30,"icon":22,"name":31,"slug":32},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",[],[],{"controls":36,"vendors":62},[37],{"slug":32,"name":38,"problem":39,"products":40},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[41,49,57],{"vendor_slug":42,"vendor_name":43,"vendor_logo":44,"product_slug":45,"product_name":46,"url":47,"description":48},"cisco","Cisco","\u002Fvendor-logos\u002Fcisco.png","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.",{"vendor_slug":50,"vendor_name":51,"vendor_logo":52,"product_slug":53,"product_name":54,"url":55,"description":56},"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":50,"vendor_name":51,"vendor_logo":52,"product_slug":58,"product_name":59,"url":60,"description":61},"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.",[],{"slug":64,"title":65,"body":66,"framework_refs":67,"framework_notes":78},"agentic-browsers-vulnerable-to-social-engineering-via-pleasefix-flaws","Agentic Browsers Vulnerable to Social Engineering via 'PleaseFix' Flaws","Agentic browsers introduce a dangerous new attack surface by automating web interactions on behalf of users, and the 'PleaseFix' vulnerabilities reveal that these systems can be socially engineered through malicious content embedded in web pages. The core weakness lies in how agentic browsers handle cross-origin requests without sufficient context validation or user intent verification, allowing attackers to hijack automated actions. This effectively resurrects cross-site request forgery (CSRF) and related attack classes that the security community spent years mitigating in traditional browsers. The stakes are significantly higher here because agentic browsers may have elevated permissions, access to sensitive accounts, and the ability to take real-world actions autonomously. Organizations deploying AI-driven browsing agents must treat them as high-risk privileged clients, not ordinary user browsers.",[68,69,70,71,72,73,74,75,76,77],"CIS Control 2: Inventory and Control of Software Assets","CIS Control 4: Secure Configuration of Enterprise Assets","CIS Control 7: Continuous Vulnerability Management","CIS Control 13: Network Monitoring and Defense","NIST SP 800-53 SI-10: Information Input Validation","NIST SP 800-53 AC-6: Least Privilege","NIST SP 800-53 SC-23: Session Authenticity","OWASP CSRF Prevention Cheat Sheet","OWASP Top 10 A05: Security Misconfiguration","NIST AI RMF: GOVERN 1.2 – AI Risk Management Policies",{}]