--- title: Grok chat duped into swallowing injected instructions description: The provided content is largely a navigation page of headline links from The Register rather than a full article, but the primary story referenced concerns... canonical: https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Grok chat duped into swallowing injected instructions | daily.dev og:description: The provided content is largely a navigation page of headline links from The Register rather than a full article, but the primary story referenced concerns... og:url: https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h og:image: https://api.daily.dev/og/posts/J8RfBAm7H.png og:image:alt: Grok chat duped into swallowing injected instructions 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. # Grok chat duped into swallowing injected instructions **[The Register](https://daily.dev/sources/theregister)** · 3 min read · 0 upvotes · 0 comments ## Summary The provided content is largely a navigation page of headline links from The Register rather than a full article, but the primary story referenced concerns researchers tricking xAI's Grok chatbot into accepting injected instructions hidden through encryption, bypassing its safety guardrails. Surrounding links touch on other AI security incidents, including Copilot being manipulated into revealing its own exploitation methods, plus unrelated infosec and open source news items. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How did researchers get Grok to follow injected instructions despite its safety filters? Researchers used encryption to disguise malicious instructions before feeding them to Grok, allowing the injected content to slip past filters designed to catch plain-text malicious prompts. Once decoded internally by the model, the hidden instructions were executed as if they were legitimate, demonstrating a prompt injection technique that evades keyword or pattern-based safety scanning. _Track emerging prompt injection techniques like this on daily.dev before they hit production systems you rely on._ ## Similar posts on daily.dev - [Hackers can turn Grok, Copilot into covert command-and-control channels, researchers warn](https://daily.dev/posts/hackers-can-turn-grok-copilot-into-covert-command-and-control-channels-researchers-warn-cjqovjm5t) · CSO Online · 0 upvotes · 0 comments --- Tags: [#ai-security](https://daily.dev/tags/ai-security), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#grok](https://daily.dev/tags/grok) [View this post on daily.dev](https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h) ```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":"Grok chat duped into swallowing injected instructions","url":"https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h"},"datePublished":"2026-08-20T13:04:51.410Z","dateModified":"2026-08-20T17:22:14.272Z","description":"The provided content is largely a navigation page of headline links from The Register rather than a full article, but the primary story referenced concerns...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f1a0e1639a036444b16b1c2a980cb59?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f1a0e1639a036444b16b1c2a980cb59?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Register","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":"The Register","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/66aa2113fdad463992ffcbf0e8963fda","url":"https://daily.dev/sources/theregister"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-security,prompt-injection,grok","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Register","item":"https://daily.dev/sources/theregister"},{"@type":"ListItem","position":3,"name":"Grok chat duped into swallowing injected instructions"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/grok-chat-duped-into-swallowing-injected-instructions-j8rfbam7h#faq","mainEntity":[{"@type":"Question","name":"How did researchers get Grok to follow injected instructions despite its safety filters?","acceptedAnswer":{"@type":"Answer","text":"Researchers used encryption to disguise malicious instructions before feeding them to Grok, allowing the injected content to slip past filters designed to catch plain-text malicious prompts. Once decoded internally by the model, the hidden instructions were executed as if they were legitimate, demonstrating a prompt injection technique that evades keyword or pattern-based safety scanning. Track emerging prompt injection techniques like this on daily.dev before they hit production systems you rely on."}}]} ```