--- title: Zero-Click IP Leak in a Privacy Search Engine: Indirect... description: A security researcher discovered a zero-click IP leak vulnerability in Kagi Search's AI Assistant feature. By embedding a hidden system instruction in a public... canonical: https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching | daily.dev og:description: A security researcher discovered a zero-click IP leak vulnerability in Kagi Search's AI Assistant feature. By embedding a hidden system instruction in a public... og:url: https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz og:image: https://api.daily.dev/og/posts/svdqrFnAZ.png og:image:alt: Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching **[InfoSec Write-ups](https://daily.dev/sources/infosecwriteups)** · 5 min read · 0 upvotes · 0 comments ## Summary A security researcher discovered a zero-click IP leak vulnerability in Kagi Search's AI Assistant feature. By embedding a hidden system instruction in a public webpage, the attacker could trick the KIMI K2.5 model into appending a Markdown image tag to its response. Because Kagi's frontend rendered external Markdown images without proxying them, the victim's browser automatically fetched the attacker-controlled URL, exposing their real IP address. The researcher reported the issue but received a dismissal marked 'Not Applicable.' Shortly after, Kagi silently patched the exact mechanism described in the report. The post highlights that the core flaw was frontend rendering of untrusted Markdown — a classic, fixable UI security issue — and criticizes the practice of silent patching without acknowledging the researcher's contribution. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [ShadowLeak Vulnerability in ChatGPT Deep Research](https://daily.dev/posts/shadowleak-vulnerability-in-chatgpt-deep-research-ubajwcvcz) · AI Cyber Insights · 0 upvotes · 0 comments - [Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents](https://daily.dev/posts/mozilla-shows-the-danger-of-indirect-prompt-injections-in-ai-coding-agents-nqhoyxkhl) · DevOps.com · 0 upvotes · 0 comments --- Tags: [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching","url":"https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz"},"datePublished":"2026-06-09T09:45:41.997Z","dateModified":"2026-06-09T09:46:18.609Z","description":"A security researcher discovered a zero-click IP leak vulnerability in Kagi Search's AI Assistant feature. By embedding a hidden system instruction in a public...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c230c2daa70715ce053f8eb942c18bcb?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c230c2daa70715ce053f8eb942c18bcb?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoSec Write-ups","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoSec Write-ups","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f0dc21b5bbfd46fda36f7b4b53dd1705","url":"https://daily.dev/sources/infosecwriteups"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/zero-click-ip-leak-in-a-privacy-search-engine-indirect-prompt-injection-silent-patching-svdqrfnaz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"prompt-injection","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoSec Write-ups","item":"https://daily.dev/sources/infosecwriteups"},{"@type":"ListItem","position":3,"name":"Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching"}]} ```