--- title: Those 'Summarize With AI' Buttons May Be Lying to You description: Microsoft researchers discovered a new attack vector called AI recommendation poisoning, where hidden instructions embedded in 'Summarize With AI' buttons... canonical: https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Those 'Summarize With AI' Buttons May Be Lying to You | daily.dev og:description: Microsoft researchers discovered a new attack vector called AI recommendation poisoning, where hidden instructions embedded in 'Summarize With AI' buttons... og:url: https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa og:image: https://api.daily.dev/og/posts/jE4UhIeoA.png og:image:alt: Those 'Summarize With AI' Buttons May Be Lying to You 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. # Those 'Summarize With AI' Buttons May Be Lying to You **[Dark Reading](https://daily.dev/sources/dr)** · 6 min read · 1 upvotes · 0 comments ## Summary Microsoft researchers discovered a new attack vector called AI recommendation poisoning, where hidden instructions embedded in 'Summarize With AI' buttons inject persistent commands into AI assistants like ChatGPT, Claude, and Microsoft 365 Copilot. Over 60 days, 50 unique poisoning attempts were observed across 31 companies in 14 industries. The attack exploits two features: URL-based prompt prefill and AI memory persistence. Turnkey tools like CiteMET NPM Package and AI Share URL Creator make it trivially easy to execute. Defenders can hunt for suspicious AI assistant URLs containing keywords like 'remember' or 'trusted source' in emails and Teams messages. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Microsoft: Poison AI buttons and links may betray your trust](https://daily.dev/posts/microsoft-poison-ai-buttons-and-links-may-betray-your-trust-y2ffwafo0) · The Register · 0 upvotes · 0 comments - [Companies are using ‘Summarize with AI’ to manipulate enterprise chatbots](https://daily.dev/posts/companies-are-using-summarize-with-ai-to-manipulate-enterprise-chatbots-bbgcshul6) · CSO Online · 0 upvotes · 0 comments - [Schneier on Security](https://daily.dev/posts/schneier-on-security-jadoaksxv) · Schneier on Security · 0 upvotes · 0 comments --- Tags: [#cyber](https://daily.dev/tags/cyber), [#microsoft](https://daily.dev/tags/microsoft), [#llm](https://daily.dev/tags/llm), [#ai-security](https://daily.dev/tags/ai-security), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa) ```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":"Those 'Summarize With AI' Buttons May Be Lying to You","url":"https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa"},"datePublished":"2026-02-23T22:51:31.790Z","dateModified":"2026-02-23T22:52:30.333Z","description":"Microsoft researchers discovered a new attack vector called AI recommendation poisoning, where hidden instructions embedded in 'Summarize With AI' buttons...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a9d5abe8985506fef60d5406d621de0e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a9d5abe8985506fef60d5406d621de0e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Dark Reading","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":"Dark Reading","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dr","url":"https://daily.dev/sources/dr"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/those-summarize-with-ai-buttons-may-be-lying-to-you-je4uhieoa","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cyber,microsoft,llm,ai-security,prompt-injection","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Dark Reading","item":"https://daily.dev/sources/dr"},{"@type":"ListItem","position":3,"name":"Those 'Summarize With AI' Buttons May Be Lying to You"}]} ```