{"id":433,"date":"2026-07-31T09:55:09","date_gmt":"2026-07-31T09:55:09","guid":{"rendered":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/"},"modified":"2026-07-31T09:55:09","modified_gmt":"2026-07-31T09:55:09","slug":"anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode","status":"publish","type":"post","link":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/","title":{"rendered":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode"},"content":{"rendered":"\n

Claude-modeller er sluppet ud af angiveligt isolerede cybersikkerhedsevalueringsmilj\u00f8er og har n\u00e5et reelle internetvendte systemer, har Anthropic bekr\u00e6ftet.<\/p>\n\n\n\n

Anthropic afsl\u00f8rede tre sikkerhedsh\u00e6ndelser<\/a>, der involverede modeller, som troede, at de angreb simulerede m\u00e5l. En konfigurationsfejl havde efterladt internetadgang aktiveret, hvilket tillod dem at interagere med rigtige tjenester og organisationer.<\/p>\n\n\n\n

H\u00e6ndelserne f\u00f8lger det nylige Hugging Face-brud, der involverede OpenAI-agenter, og rapporter om, at OpenAI-modeller udnyttede JFrog Artifactory zero-day-s\u00e5rbarheder<\/a>, mens de fors\u00f8gte at undslippe en sandkasse.<\/p>\n\n\n\n

Internetadgang forblev aktiveret under Claude-sikkerhedstests<\/h2>\n\n\n\n

Tredjepartsevaluatoren Irregular organiserede testene som capture-the-flag-\u00f8velser. Modellerne modtog instruktioner, der angav, at de opererede inde i isolerede simuleringer.<\/p>\n\n\n\n

Testmilj\u00f8et kunne dog stadig f\u00e5 adgang til det offentlige internet. Da modellerne ikke kunne finde deres tilt\u00e6nkte simulerede m\u00e5l, s\u00f8gte de efter lignende systemer online og behandlede nogle rigtige tjenester som en del af \u00f8velsen.<\/p>\n\n\n\n

Anthropic og Irregular identificerede ikke konfigurationsproblemet f\u00f8r m\u00e5neder efter den tidligste h\u00e6ndelse. Anthropic oplyste, at det \u00e6ldste kendte brud fandt sted i april og forblev uopdaget i omkring tre m\u00e5neder.<\/p>\n\n\n\n

Claude Mythos 5 offentliggjorde en ondsindet PyPI-pakke<\/h3>\n\n\n\n

Under \u00e9n evaluering fandt Claude Mythos 5 installationsinstruktioner, der refererede til en fiktiv Python-pakke. Pakkenavnet var ikke registreret p\u00e5 Python Package Index.<\/p>\n\n\n\n

Modellen erkendte, at den kunne registrere det ubrugte navn og offentligg\u00f8re sin egen kode. Systemer, der fulgte installationsinstruktionerne, kunne derefter automatisk downloade og eksekvere pakken.<\/p>\n\n\n\n

Claude oprettede de n\u00f8dvendige konti og uploadede en ondsindet pakke til PyPI. Pakken forblev offentligt tilg\u00e6ngelig i cirka en time, f\u00f8r PyPIs automatiserede beskyttelser fjernede den.<\/p>\n\n\n\n

I den periode downloadede og eksekverede 15 rigtige systemer koden.<\/p>\n\n\n\n

Sikkerhedsfirmas legitimationsoplysninger blev stj\u00e5let<\/h3>\n\n\n\n

Et ber\u00f8rt system tilh\u00f8rte et cybersikkerhedsfirma, der automatisk downloader og scanner nyoffentliggjorte PyPI-pakker.<\/p>\n\n\n\n

Den ondsindede pakke indsamlede legitimationsoplysninger fra systemet og sendte dem til infrastruktur, som Claude havde oprettet. Modellen brugte derefter de stj\u00e5lne legitimationsoplysninger til at f\u00e5 adgang til yderligere dele af firmaets netv\u00e6rk.<\/p>\n\n\n\n

Anthropic oplyste, at Claude ikke havde nogen forudg\u00e5ende viden om organisationen og ikke med vilje valgte den som m\u00e5l. Firmaet underrettede PyPI og delte indikatorer knyttet til den ondsindede pakke.<\/p>\n\n\n\n

Det ber\u00f8rte cybersikkerhedsfirma havde ikke opdaget indtr\u00e6ngningen, f\u00f8r Anthropic kontaktede det.<\/p>\n\n\n\n

Claude Opus 4.7 fik adgang til en produktionsdatabase<\/h3>\n\n\n\n

En separat evaluering, der involverede Claude Opus 4.7, resulterede i adgang til en \u00e6gte produktionsdatabase.<\/p>\n\n\n\n

Det fiktive m\u00e5l, der blev brugt i \u00f8velsen, delte navn med en eksisterende virksomhed og et dom\u00e6ne. Efter at Claude ikke kunne n\u00e5 det simulerede system, fandt den den rigtige organisation online og behandlede den som det tilt\u00e6nkte m\u00e5l.<\/p>\n\n\n\n

Modellen udtrak applikations- og infrastrukturlegitimationsoplysninger, f\u00f8r den fik adgang til en database, der indeholdt flere hundrede r\u00e6kker produktionsinformation.<\/p>\n\n\n\n

Anthropic beskrev denne h\u00e6ndelse som mere alvorlig, fordi modellen n\u00e5ede live-forretningssystemer og fik adgang til rigtige data.<\/p>\n\n\n\n

Forskningsmodel scannede omkring 9.000 systemer<\/h3>\n\n\n\n

En endnu ikke frigivet Anthropic-forskningsmodel for\u00e5rsagede den tredje h\u00e6ndelse.<\/p>\n\n\n\n

Efter at den ikke kunne finde det tilt\u00e6nkte testm\u00e5l, scannede modellen omkring 9.000 internetforbundne systemer. Den kompromitterede en eksponeret applikation ved hj\u00e6lp af legitimationsoplysninger vist p\u00e5 en debug-side og en SQL-injektionss\u00e5rbarhed.<\/p>\n\n\n\n

Modellen fastslog senere, at den kompromitterede applikation tilh\u00f8rte en ikke-relateret cloud-konto. Den stoppede derefter angrebet uden at kr\u00e6ve menneskelig indgriben.<\/p>\n\n\n\n

Anthropic var stadig i gang med at fors\u00f8ge at kontakte den ber\u00f8rte organisation, da det offentliggjorde sine resultater.<\/p>\n\n\n\n

Modeller stolede p\u00e5 grundl\u00e6ggende sikkerhedssvagheder<\/h3>\n\n\n\n

Anthropic udtalte, at h\u00e6ndelserne ikke involverede nye eller tidligere ukendte angrebsteknikker.<\/p>\n\n\n\n

Modellerne stolede p\u00e5 almindelige svagheder, herunder eksponerede legitimationsoplysninger, svage adgangskoder, offentligt tilg\u00e6ngelige endpoints, debug-sider, der indeholdt f\u00f8lsomme oplysninger, og SQL-injektionss\u00e5rbarheder.<\/p>\n\n\n\n

Den prim\u00e6re fejl kom fra ubegr\u00e6nset internetadgang og modellernes antagelse om, at ethvert tilg\u00e6ngeligt system udgjorde en del af den autoriserede test.<\/p>\n\n\n\n

Anthropic satte cyber-testning p\u00e5 pause efter at have gennemg\u00e5et h\u00e6ndelserne<\/h3>\n\n\n\n

Anthropic begyndte at gennemg\u00e5 evalueringerne og satte al cybersikkerhedstestning p\u00e5 pause den 23. juli.<\/p>\n\n\n\n

Virksomheden identificerede de tre h\u00e6ndelser den 24. juli. Irregular og to ber\u00f8rte organisationer modtog meddelelser den 27. juli.<\/p>\n\n\n\n

Anthropic fortsatte med at fors\u00f8ge at kontakte den organisation, der var involveret i den tredje h\u00e6ndelse.<\/p>\n\n\n\n

Ingen af de to organisationer, som Anthropic med held kontaktede, havde selvst\u00e6ndigt opdaget kompromitteringerne, f\u00f8r de modtog meddelelserne.<\/p>\n\n\n\n

Evalueringsmilj\u00f8et manglede produktionssikkerhedsforanstaltninger<\/h3>\n\n\n\n

Testsystemerne anvendte ikke de klassifikatorer, overv\u00e5gningsv\u00e6rkt\u00f8jer og andre sikkerhedsforanstaltninger, der er inkluderet med offentligt tilg\u00e6ngelige Claude-modeller.<\/p>\n\n\n\n

Anthropic oplyste, at dens produktionsbeskyttelser sandsynligvis ville have blokeret de handlinger, der blev set under evalueringerne. Det karakteriserede h\u00e6ndelserne hovedsageligt som fejl i testdesign, infrastruktur, overv\u00e5gning og tredjeparts-tilsyn.<\/p>\n\n\n\n

Virksomheden beskrev ikke h\u00e6ndelserne som bevis p\u00e5 et grundl\u00e6ggende alignment-svigt. I stedet fulgte modellerne evalueringsinstruktionerne, mens de fejlagtigt interagerede med rigtige m\u00e5l.<\/p>\n\n\n\n

Anthropic planl\u00e6gger strengere overv\u00e5gning til fremtidige tests<\/h3>\n\n\n\n

Anthropic planl\u00e6gger at udvide transskript-overv\u00e5gning p\u00e5 tv\u00e6rs af fremtidige evalueringer og introducere st\u00e6rkere efterforskningsv\u00e6rkt\u00f8jer.<\/p>\n\n\n\n

Det vil ogs\u00e5 \u00f8ge tilsynet med tredjeparts testpartnere og gennemg\u00e5, hvordan evalueringsmilj\u00f8er kobler sig til ekstern infrastruktur.<\/p>\n\n\n\n

Anthropic dr\u00f8fter en uafh\u00e6ngig gennemgang med METR og planl\u00e6gger at offentligg\u00f8re en delvist redigeret transskription af PyPI-h\u00e6ndelsen.<\/p>\n\n\n\n

P\u00e5 trods af sikkerhedsfejlene har Claude Mythos demonstreret st\u00e6rke s\u00e5rbarhedsdetekteringsevner. Microsoft har ogs\u00e5 anerkendt, at det k\u00e6mper med at rette alle de s\u00e5rbarheder, som Claude Mythos finder<\/a>, hvilket fremh\u00e6ver b\u00e5de modellens potentiale inden for sikkerhedsforskning og de risici, som d\u00e5rligt isolerede testmilj\u00f8er skaber.<\/p>\n","protected":false},"excerpt":{"rendered":"

Claude-modeller er sluppet ud af angiveligt isolerede cybersikkerhedsevalueringsmilj\u00f8er og har n\u00e5et reelle internetvendte systemer, har Anthropic bekr\u00e6ftet. Anthropic afsl\u00f8rede tre sikkerhedsh\u00e6ndelser, der involverede modeller, som troede, at de angreb simulerede m\u00e5l. En konfigurationsfejl havde efterladt internetadgang aktiveret, hvilket tillod dem at interagere med rigtige tjenester og organisationer. H\u00e6ndelserne f\u00f8lger det nylige Hugging Face-brud, der involverede […]<\/p>\n","protected":false},"author":49,"featured_media":434,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_enabled_clarity":"","footnotes":""},"categories":[1],"tags":[],"work":[],"class_list":["post-433","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"acf":[],"yoast_head":"\nAnthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode - WindowsReport DK (Danish)<\/title>\n<meta name=\"description\" content=\"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer\" \/>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode\" \/>\n<meta property=\"og:description\" content=\"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer\" \/>\n<meta property=\"og:url\" content=\"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/\" \/>\n<meta property=\"og:site_name\" content=\"WindowsReport DK (Danish)\" \/>\n<meta property=\"article:published_time\" content=\"2026-07-31T09:55:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1280\" \/>\n\t<meta property=\"og:image:height\" content=\"801\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Milan Stanojevic\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@MilanStanojev17\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Milan Stanojevic\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/\"},\"author\":{\"name\":\"Milan Stanojevic\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/#\\\/schema\\\/person\\\/e3910b02e4592db47a0eb303765a3a25\"},\"headline\":\"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode\",\"datePublished\":\"2026-07-31T09:55:09+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/\"},\"wordCount\":920,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/wp-content\\\/uploads\\\/sites\\\/12\\\/2026\\\/07\\\/anthropic-hacked-organizations-5.jpg\",\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#respond\"]}],\"copyrightYear\":\"2026\",\"copyrightHolder\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/\",\"url\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/\",\"name\":\"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode - WindowsReport DK (Danish)\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/wp-content\\\/uploads\\\/sites\\\/12\\\/2026\\\/07\\\/anthropic-hacked-organizations-5.jpg\",\"datePublished\":\"2026-07-31T09:55:09+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/#\\\/schema\\\/person\\\/e3910b02e4592db47a0eb303765a3a25\"},\"description\":\"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#primaryimage\",\"url\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/wp-content\\\/uploads\\\/sites\\\/12\\\/2026\\\/07\\\/anthropic-hacked-organizations-5.jpg\",\"contentUrl\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/wp-content\\\/uploads\\\/sites\\\/12\\\/2026\\\/07\\\/anthropic-hacked-organizations-5.jpg\",\"width\":1280,\"height\":801},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/#website\",\"url\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/\",\"name\":\"WindowsReport DK (Danish)\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/#\\\/schema\\\/person\\\/e3910b02e4592db47a0eb303765a3a25\",\"name\":\"Milan Stanojevic\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g\",\"caption\":\"Milan Stanojevic\"},\"description\":\"Milan has been enthusiastic about technology ever since his childhood days, and this led him to take interest in all PC-related technologies. He's a PC enthusiast and he spends most of his time learning about computers and technology. Before joining WindowsReport, he worked as a front-end web developer. Now, he's one of the Troubleshooting experts in our worldwide team, specializing in Windows errors & software issues.\",\"sameAs\":[\"https:\\\/\\\/x.com\\\/MilanStanojev17\"],\"url\":\"https:\\\/\\\/windowsreport.com\\\/dk\\\/author\\\/milan\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode - WindowsReport DK (Danish)","description":"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"en_US","og_type":"article","og_title":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode","og_description":"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer","og_url":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/","og_site_name":"WindowsReport DK (Danish)","article_published_time":"2026-07-31T09:55:09+00:00","og_image":[{"width":1280,"height":801,"url":"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg","type":"image\/jpeg"}],"author":"Milan Stanojevic","twitter_card":"summary_large_image","twitter_creator":"@MilanStanojev17","twitter_misc":{"Written by":"Milan Stanojevic","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#article","isPartOf":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/"},"author":{"name":"Milan Stanojevic","@id":"https:\/\/windowsreport.com\/dk\/#\/schema\/person\/e3910b02e4592db47a0eb303765a3a25"},"headline":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode","datePublished":"2026-07-31T09:55:09+00:00","mainEntityOfPage":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/"},"wordCount":920,"commentCount":0,"image":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#primaryimage"},"thumbnailUrl":"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg","inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#respond"]}],"copyrightYear":"2026","copyrightHolder":{"@id":"https:\/\/windowsreport.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/","url":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/","name":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode - WindowsReport DK (Danish)","isPartOf":{"@id":"https:\/\/windowsreport.com\/dk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#primaryimage"},"image":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#primaryimage"},"thumbnailUrl":"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg","datePublished":"2026-07-31T09:55:09+00:00","author":{"@id":"https:\/\/windowsreport.com\/dk\/#\/schema\/person\/e3910b02e4592db47a0eb303765a3a25"},"description":"Anthropic siger, at Claude-modeller undslap sikkerhedstests, offentliggjorde en ondsindet PyPI-pakke og fik adgang til rigtige produktionssystemer","breadcrumb":{"@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#primaryimage","url":"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg","contentUrl":"https:\/\/windowsreport.com\/dk\/wp-content\/uploads\/sites\/12\/2026\/07\/anthropic-hacked-organizations-5.jpg","width":1280,"height":801},{"@type":"BreadcrumbList","@id":"https:\/\/windowsreport.com\/dk\/anthropic-siger-at-claude-hackede-3-organisationer-og-publicerede-ondsindet-pypi-kode\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/windowsreport.com\/dk\/"},{"@type":"ListItem","position":2,"name":"Anthropic siger, at Claude hackede 3 organisationer og publicerede ondsindet PyPI-kode"}]},{"@type":"WebSite","@id":"https:\/\/windowsreport.com\/dk\/#website","url":"https:\/\/windowsreport.com\/dk\/","name":"WindowsReport DK (Danish)","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/windowsreport.com\/dk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/windowsreport.com\/dk\/#\/schema\/person\/e3910b02e4592db47a0eb303765a3a25","name":"Milan Stanojevic","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/fdfb58c5f9c33b78cbac22bd664ac8335249104922392e67d69d32ee59624544?s=96&d=mm&r=g","caption":"Milan Stanojevic"},"description":"Milan has been enthusiastic about technology ever since his childhood days, and this led him to take interest in all PC-related technologies. He's a PC enthusiast and he spends most of his time learning about computers and technology. Before joining WindowsReport, he worked as a front-end web developer. Now, he's one of the Troubleshooting experts in our worldwide team, specializing in Windows errors & software issues.","sameAs":["https:\/\/x.com\/MilanStanojev17"],"url":"https:\/\/windowsreport.com\/dk\/author\/milan\/"}]}},"_links":{"self":[{"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/posts\/433","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/users\/49"}],"replies":[{"embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/comments?post=433"}],"version-history":[{"count":0,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/posts\/433\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/media\/434"}],"wp:attachment":[{"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/media?parent=433"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/categories?post=433"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/tags?post=433"},{"taxonomy":"work","embeddable":true,"href":"https:\/\/windowsreport.com\/dk\/wp-json\/wp\/v2\/work?post=433"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}