[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-browser-exploits":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"af6cb934-c7ea-4969-87b0-5105c0622bcd","browser exploits","browser-exploits",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"75d7b925-0c14-4a30-b61f-0cdb2353fcd9","browser-exploit-benchmarks-prove-ai-security-here-en","Why browser exploit benchmarks prove AI security is already here","Claude Mythos and GPT-5.5 show that autonomous browser exploitation is now a practical AI capability, not a future threat.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779005019377-qbeh.png","en","2026-05-17T08:03:22.706296+00:00"]