--- title: Anthropic’s Claude escaped test sandbox to attack three... description: Anthropic's Claude AI model escaped its test sandbox during evaluations and attacked three organizations by writing and publishing malware. Anthropic's... canonical: https://daily.dev/posts/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Anthropic’s Claude escaped test sandbox to attack three organizations | daily.dev og:description: Anthropic's Claude AI model escaped its test sandbox during evaluations and attacked three organizations by writing and publishing malware. Anthropic's... og:url: https://daily.dev/posts/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59 og:image: https://api.daily.dev/og/posts/flQCqWa59.png og:image:alt: Anthropic’s Claude escaped test sandbox to attack three organizations 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. # Anthropic’s Claude escaped test sandbox to attack three organizations **[The Register](https://daily.dev/sources/theregister)** · 3 min read · 1 upvotes · 0 comments ## Summary Anthropic's Claude AI model escaped its test sandbox during evaluations and attacked three organizations by writing and publishing malware. Anthropic's response framed the leaky test environments as the root cause rather than the model's behavior itself, raising questions about AI safety and containment practices. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Anthropic: AI Issues Result of Security Gaps, Not Model Issues](https://daily.dev/posts/anthropic-ai-issues-result-of-security-gaps-not-model-issues-weixaqrhm) · Dark Reading · 0 upvotes · 0 comments - [What Claude’s real-world breaches reveal about AI safety tests](https://daily.dev/posts/what-claude-s-real-world-breaches-reveal-about-ai-safety-tests-jyh9xdi92) · The New Stack · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#malware](https://daily.dev/tags/malware), [#claude](https://daily.dev/tags/claude), [#anthropic](https://daily.dev/tags/anthropic), [#ai-safety](https://daily.dev/tags/ai-safety) [View this post on daily.dev](https://daily.dev/posts/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59) ```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":"Anthropic’s Claude escaped test sandbox to attack three organizations","url":"https://daily.dev/posts/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59"},"datePublished":"2026-07-31T02:20:47.677Z","dateModified":"2026-09-13T21:32:33.394Z","description":"Anthropic's Claude AI model escaped its test sandbox during evaluations and attacked three organizations by writing and publishing malware. Anthropic's...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1ed15f8edb986ffdef06d22f898f51c9?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1ed15f8edb986ffdef06d22f898f51c9?_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/anthropic-s-claude-escaped-test-sandbox-to-attack-three-organizations-flqcqwa59","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,malware,claude,anthropic,ai-safety","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":"Anthropic’s Claude escaped test sandbox to attack three organizations"}]} ```