--- title: Chain-of-Thought Spoofing Targets Reasoning AI Models description: Researchers have demonstrated a new attack called CoT (Chain of Thought) Forgery that exploits how LLMs prioritize writing style over metadata tags. By... canonical: https://daily.dev/posts/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Chain-of-Thought Spoofing Targets Reasoning AI Models | daily.dev og:description: Researchers have demonstrated a new attack called CoT (Chain of Thought) Forgery that exploits how LLMs prioritize writing style over metadata tags. By... og:url: https://daily.dev/posts/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef og:image: https://api.daily.dev/og/posts/qu5wRcbef.png og:image:alt: Chain-of-Thought Spoofing Targets Reasoning AI Models 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. # Chain-of-Thought Spoofing Targets Reasoning AI Models **[Hackaday](https://daily.dev/sources/hackaday)** · 3 min read · 0 upvotes · 0 comments ## Summary Researchers have demonstrated a new attack called CoT (Chain of Thought) Forgery that exploits how LLMs prioritize writing style over metadata tags. By crafting text that mimics a model's internal reasoning style (the tag), attackers can trick the model into treating injected content as already-reached conclusions — bypassing role-based trust hierarchies. The attack builds on classic prompt injection but is more sophisticated, exploiting the fact that LLMs cannot cleanly separate instruction sources from data. The researchers argue this class of attack will remain an evolving challenge rather than a solved problem, given LLMs' single-channel architecture and the creativity of adversaries. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [A fundamental flaw leaves LLMs strikingly vulnerable to attack](https://daily.dev/posts/a-fundamental-flaw-leaves-llms-strikingly-vulnerable-to-attack-lpupepbpf) · MIT Technology Review · 1 upvotes · 0 comments --- Tags: [#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/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef) ```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":"Chain-of-Thought Spoofing Targets Reasoning AI Models","url":"https://daily.dev/posts/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef"},"datePublished":"2026-07-03T02:28:10.561Z","dateModified":"2026-07-03T02:28:29.744Z","description":"Researchers have demonstrated a new attack called CoT (Chain of Thought) Forgery that exploits how LLMs prioritize writing style over metadata tags. By...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/177330afa3d85883a07623af3fbac8c3?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/177330afa3d85883a07623af3fbac8c3?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hackaday","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":"Hackaday","logo":"https://media.daily.dev/image/upload/s--JhDfhy70--/f_auto,q_auto/v1767541814/logos/hackaday","url":"https://daily.dev/sources/hackaday"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/chain-of-thought-spoofing-targets-reasoning-ai-models-qu5wrcbef","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-security,prompt-injection","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hackaday","item":"https://daily.dev/sources/hackaday"},{"@type":"ListItem","position":3,"name":"Chain-of-Thought Spoofing Targets Reasoning AI Models"}]} ```