{"id":4719,"date":"2026-07-31T02:05:43","date_gmt":"2026-07-31T02:05:43","guid":{"rendered":"https:\/\/silvybrand.com\/?p=4719"},"modified":"2026-07-31T02:05:43","modified_gmt":"2026-07-31T02:05:43","slug":"anthropic-says-claude-hacked-real-systems-during-cybersecurity-tests","status":"publish","type":"post","link":"https:\/\/silvybrand.com\/?p=4719","title":{"rendered":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests"},"content":{"rendered":"<p><br \/>\n<\/p>\n<div>\n<p><span class=\"lead-in-text-callout\">Anthropic disclosed on<\/span> Thursday that its <a href=\"https:\/\/www.wired.com\/story\/model-behavior-anthropic-will-charge-consumers-extra-to-use-claude-fable-5\/\" class=\"text link\">AI models<\/a> gained unauthorized access to the systems of three different unnamed organizations during cybersecurity testing. The company says <a href=\"https:\/\/www.wired.com\/story\/private-claude-chats-exposed-in-google-and-bing-search-results\/\" class=\"text link\">Claude<\/a> reached the internet \u201cfrom within or while interacting&#8221; with a third-party evaluation environment. The announcement comes more than a week after OpenAI revealed that one of its AI agents <a href=\"https:\/\/www.wired.com\/story\/openai-models-escaped-containment-and-hacked-huggingface\/\" class=\"text link\">hacked into Hugging Face<\/a> during a separate cybersecurity test.<\/p>\n<p class=\"paywall\">The discovery came after Anthropic decided to conduct \u201ca large-scale retrospective review of our own cybersecurity evaluations\u201d following the OpenAI incident, according to a <a data-offer-url=\"https:\/\/www.anthropic.com\/news\/investigating-incidents-cybersecurity-evals\" class=\"external-link text link\" data-event-click=\"{&quot;element&quot;:&quot;ExternalLink&quot;,&quot;outgoingURL&quot;:&quot;https:\/\/www.anthropic.com\/news\/investigating-incidents-cybersecurity-evals&quot;}\" href=\"https:\/\/www.anthropic.com\/news\/investigating-incidents-cybersecurity-evals\" rel=\"nofollow noopener\" target=\"_blank\">blog post<\/a> Anthropic published Thursday. The AI lab says it first identified 141,006 tests in which it determined that Claude could have obtained internet access. It then found that three different Claude models accessed the internet in evaluations run by the third-party AI testing firm Irregular, and then hacked into the production infrastructure of three different organizations.<\/p>\n<p class=\"paywall\">Anthropic said that the incidents involved Opus 4.7, <a href=\"https:\/\/www.wired.com\/story\/anthropic-restores-access-to-mythos\/\" class=\"text link\">Mythos 5<\/a>, and an internal research test model. The earliest incidents happened in April\u2014meaning they likely went unnoticed publicly for months. Just like in the OpenAI case, Anthropic had deliberately turned off safeguards designed to constrain the AI models and prevent them from being misused. In other words, these weren\u2019t the versions released to the public.<\/p>\n<p class=\"paywall\">\u201cIn all three incidents, Claude had been tasked with a capture-the-flag challenge, one of the ways we assess a model\u2019s cyber capabilities,\u201d Anthropic said in its blog post. The company added that in all of the cases, \u201cAnthropic\u2019s evaluation prompt specified to Claude that its environment was a simulation and that it had no internet access.\u201d It attributed the oversight to a \u201cmisunderstanding\u201d between Anthropic and Irregular.<\/p>\n<p class=\"paywall\">While Claude wasn\u2019t supposed to have internet access, Anthropic said that Irregular had misconfigured the machines that it was using to test Claude, giving the AI models the ability to surf the web. \u201cNeither we nor our evaluation partner were aware of this misconfiguration until we detected it through our additional evaluation monitoring last week,\u201d Anthropic said in the blog post.<\/p>\n<p class=\"paywall\">\u201cWe now have evidence confirming that both of the two largest AI labs have not only failed to contain their agents, but also failed to detect their jailbreaks in real time,\u201d says Jake Williams, vice president of research and development at Hunter Strategy. \u201cIt&#8217;s clear that regulation and government oversight for AI testing is needed immediately.\u201d<\/p>\n<p class=\"paywall\">Irregular and Anthropic did not immediately respond to requests for comment.<\/p>\n<p class=\"paywall\">Unlike in the OpenAI case, Anthropic said that Claude did not find or exploit any complex vulnerabilities. Instead, it relied on basic techniques, \u201csuch as exploiting weak passwords and unauthenticated endpoints.\u201d<\/p>\n<p class=\"paywall\">OpenAI said that its AI agent accessed the internet by exploiting a zero-day vulnerability. But it went on to access the systems of <a href=\"https:\/\/www.wired.com\/story\/openais-rogue-ai-agent-hacked-more-than-just-hugging-face\/\" class=\"text link\">multiple third-party organizations<\/a> using the same variety of everyday cybersecurity weaknesses as Anthropic\u2019s models. Specifically, OpenAI said the AI agent apparently found credentials that had been exposed on the open internet.<\/p>\n<p class=\"paywall\">Anthropic acknowledged that if the AI lab and its testing partner implemented more \u201cdefense-in-depth\u201d measures, they could have prevented the incidents, or at least reduced the likelihood of them occurring, echoing OpenAI\u2019s response to <a href=\"https:\/\/www.wired.com\/story\/openais-hacking-debacle-was-a-human-mistake\/\" class=\"text link\">mounting criticism<\/a> over its own incident.<\/p>\n<p class=\"paywall\">\u201cI don&#8217;t understand how any of these AI labs are playing this off like this is &#8216;just something that happens,&#8217;\u201d Williams says. \u201cIt&#8217;s not. It&#8217;s negligence.\u201d<\/p>\n<p class=\"paywall\">The AI lab stressed that the models were told they didn\u2019t have access to the open internet, and for the most part, Claude mistook the organizations it accessed as being part of the testing environment. Put differently, the models largely didn\u2019t understand that they had escaped containment to begin with.<\/p>\n<\/div>\n<p><br \/>\n<br \/><a href=\"https:\/\/www.wired.com\/story\/anthropic-says-claude-hacked-real-systems-during-cybersecurity-tests\/\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Anthropic disclosed on Thursday that its AI models gained unauthorized access to the systems of three different unnamed organizations during cybersecurity testing. The company says Claude reached the internet \u201cfrom within or while interacting&#8221; with a third-party evaluation environment. The announcement comes more than a week after OpenAI revealed that one of its AI agents [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":4720,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9],"tags":[175,83,174,250,350,78],"class_list":["post-4719","post","type-post","status-publish","format-standard","has-post-thumbnail","category-gadgets","tag-anthropic","tag-artificial-intelligence","tag-claude","tag-cybersecurity","tag-hacking","tag-openai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog<\/title>\n<meta name=\"description\" content=\"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/silvybrand.com\/?p=4719\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog\" \/>\n<meta property=\"og:description\" content=\"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/silvybrand.com\/?p=4719\" \/>\n<meta property=\"og:site_name\" content=\"Silvybrand Lifestyle Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-07-31T02:05:43+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1250\" \/>\n\t<meta property=\"og:image:height\" content=\"654\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"SILVYBRAND\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"SILVYBRAND\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719\"},\"author\":{\"name\":\"SILVYBRAND\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#\\\/schema\\\/person\\\/8bdc6818a5b6ef5b9745e468818e37f3\"},\"headline\":\"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests\",\"datePublished\":\"2026-07-31T02:05:43+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719\"},\"wordCount\":627,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Business_Claude-Escape.jpg\",\"keywords\":[\"anthropic\",\"artificial intelligence\",\"claude\",\"cybersecurity\",\"hacking\",\"openai\"],\"articleSection\":[\"Gadgets\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/silvybrand.com\\\/?p=4719#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719\",\"url\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719\",\"name\":\"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Business_Claude-Escape.jpg\",\"datePublished\":\"2026-07-31T02:05:43+00:00\",\"description\":\"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/silvybrand.com\\\/?p=4719\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#primaryimage\",\"url\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Business_Claude-Escape.jpg\",\"contentUrl\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Business_Claude-Escape.jpg\",\"width\":1250,\"height\":654},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/?p=4719#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/silvybrand.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#website\",\"url\":\"https:\\\/\\\/silvybrand.com\\\/\",\"name\":\"Silvybrand Lifestyle Blog\",\"description\":\"Your daily dose of lifestyle, fashion, travel, beauty, and inspiration \u2014 living boldly, stylishly, and confidently.\",\"publisher\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/silvybrand.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#organization\",\"name\":\"Silvybrand Lifestyle Blog\",\"url\":\"https:\\\/\\\/silvybrand.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/05\\\/SILVYBRAND-LOGO.jpg\",\"contentUrl\":\"https:\\\/\\\/silvybrand.com\\\/wp-content\\\/uploads\\\/2026\\\/05\\\/SILVYBRAND-LOGO.jpg\",\"width\":1115,\"height\":522,\"caption\":\"Silvybrand Lifestyle Blog\"},\"image\":{\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/silvybrand.com\\\/#\\\/schema\\\/person\\\/8bdc6818a5b6ef5b9745e468818e37f3\",\"name\":\"SILVYBRAND\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g\",\"caption\":\"SILVYBRAND\"},\"sameAs\":[\"https:\\\/\\\/silvybrand.com\"],\"url\":\"https:\\\/\\\/silvybrand.com\\\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog","description":"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/silvybrand.com\/?p=4719","og_locale":"en_US","og_type":"article","og_title":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog","og_description":"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.","og_url":"https:\/\/silvybrand.com\/?p=4719","og_site_name":"Silvybrand Lifestyle Blog","article_published_time":"2026-07-31T02:05:43+00:00","og_image":[{"width":1250,"height":654,"url":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg","type":"image\/jpeg"}],"author":"SILVYBRAND","twitter_card":"summary_large_image","twitter_misc":{"Written by":"SILVYBRAND","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/silvybrand.com\/?p=4719#article","isPartOf":{"@id":"https:\/\/silvybrand.com\/?p=4719"},"author":{"name":"SILVYBRAND","@id":"https:\/\/silvybrand.com\/#\/schema\/person\/8bdc6818a5b6ef5b9745e468818e37f3"},"headline":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests","datePublished":"2026-07-31T02:05:43+00:00","mainEntityOfPage":{"@id":"https:\/\/silvybrand.com\/?p=4719"},"wordCount":627,"commentCount":0,"publisher":{"@id":"https:\/\/silvybrand.com\/#organization"},"image":{"@id":"https:\/\/silvybrand.com\/?p=4719#primaryimage"},"thumbnailUrl":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg","keywords":["anthropic","artificial intelligence","claude","cybersecurity","hacking","openai"],"articleSection":["Gadgets"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/silvybrand.com\/?p=4719#respond"]}]},{"@type":"WebPage","@id":"https:\/\/silvybrand.com\/?p=4719","url":"https:\/\/silvybrand.com\/?p=4719","name":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests - Silvybrand Lifestyle Blog","isPartOf":{"@id":"https:\/\/silvybrand.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/silvybrand.com\/?p=4719#primaryimage"},"image":{"@id":"https:\/\/silvybrand.com\/?p=4719#primaryimage"},"thumbnailUrl":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg","datePublished":"2026-07-31T02:05:43+00:00","description":"In a review triggered by OpenAI\u2019s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.","breadcrumb":{"@id":"https:\/\/silvybrand.com\/?p=4719#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/silvybrand.com\/?p=4719"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/silvybrand.com\/?p=4719#primaryimage","url":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg","contentUrl":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/07\/Business_Claude-Escape.jpg","width":1250,"height":654},{"@type":"BreadcrumbList","@id":"https:\/\/silvybrand.com\/?p=4719#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/silvybrand.com\/"},{"@type":"ListItem","position":2,"name":"Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests"}]},{"@type":"WebSite","@id":"https:\/\/silvybrand.com\/#website","url":"https:\/\/silvybrand.com\/","name":"Silvybrand Lifestyle Blog","description":"Your daily dose of lifestyle, fashion, travel, beauty, and inspiration \u2014 living boldly, stylishly, and confidently.","publisher":{"@id":"https:\/\/silvybrand.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/silvybrand.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/silvybrand.com\/#organization","name":"Silvybrand Lifestyle Blog","url":"https:\/\/silvybrand.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/silvybrand.com\/#\/schema\/logo\/image\/","url":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/05\/SILVYBRAND-LOGO.jpg","contentUrl":"https:\/\/silvybrand.com\/wp-content\/uploads\/2026\/05\/SILVYBRAND-LOGO.jpg","width":1115,"height":522,"caption":"Silvybrand Lifestyle Blog"},"image":{"@id":"https:\/\/silvybrand.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/silvybrand.com\/#\/schema\/person\/8bdc6818a5b6ef5b9745e468818e37f3","name":"SILVYBRAND","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e7db54afd7d090e59e1a481fd3e6812d467eb2a3b81e7a3092023acfc59a496b?s=96&d=mm&r=g","caption":"SILVYBRAND"},"sameAs":["https:\/\/silvybrand.com"],"url":"https:\/\/silvybrand.com\/?author=1"}]}},"_links":{"self":[{"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/posts\/4719","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/silvybrand.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4719"}],"version-history":[{"count":0,"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/posts\/4719\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/silvybrand.com\/index.php?rest_route=\/wp\/v2\/media\/4720"}],"wp:attachment":[{"href":"https:\/\/silvybrand.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4719"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/silvybrand.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4719"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/silvybrand.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4719"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}