1.0https://veritasai.ai/nlBryanhttps://veritasai.ai/nl/author/bryan/Prompt injection: what it is and how to test your AI for it -rich600338<blockquote class="wp-embedded-content" data-secret="7ZyGElr0Vj"><a href="https://veritasai.ai/nl/prompt-injection-testing/">Prompt injection: what it is and how to test your AI for it</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://veritasai.ai/nl/prompt-injection-testing/embed/#?secret=7ZyGElr0Vj" width="600" height="338" title="“Prompt injection: what it is and how to test your AI for it” — " data-secret="7ZyGElr0Vj" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script>
/*! This file is auto-generated */
!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);
//# sourceURL=https://veritasai.ai/wp-includes/js/wp-embed.min.js
</script>Prompt injection tricks an AI into ignoring its own rules. It tops the OWASP list of LLM risks. Here is how it works, why filters alone don't stop it, and how to test for it.