{"version":"1.0","provider_name":"AI GRID","provider_url":"https:\/\/ai-grid.org\/en","title":"Security-Insider: KI-Modelle au\u00dfer Kontrolle? - AI GRID","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"VIQpU1Ra0k\"><a href=\"https:\/\/ai-grid.org\/en\/news\/security-insider-ki-modelle-ausser-kontrolle\/\">Security-Insider: KI-Modelle au\u00dfer Kontrolle?<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/ai-grid.org\/en\/news\/security-insider-ki-modelle-ausser-kontrolle\/embed\/#?secret=VIQpU1Ra0k\" width=\"600\" height=\"338\" title=\"&#8220;Security-Insider: KI-Modelle au\u00dfer Kontrolle?&#8221; &#8212; AI GRID\" data-secret=\"VIQpU1Ra0k\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script>\n\/*! This file is auto-generated *\/\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!\/[^a-zA-Z0-9]\/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n\/\/# sourceURL=https:\/\/ai-grid.org\/wp-includes\/js\/wp-embed.min.js\n<\/script>","thumbnail_url":"https:\/\/ai-grid.org\/wp-content\/uploads\/2026\/10\/Bildschirmfoto-2026-10-19-um-15.05.34.png","thumbnail_width":946,"thumbnail_height":804,"description":"AI Grid member Felix M\u00e4chtle examines what recent cyber tests involving models from OpenAI, Anthropic and AISI reveal. The incidents show that AI security requires robust systems security, clear boundaries and human oversight."}