{"id":14872,"date":"2026-08-06T12:00:33","date_gmt":"2026-08-06T12:00:33","guid":{"rendered":"https:\/\/news.theck1.no\/?p=14872"},"modified":"2026-08-06T12:00:33","modified_gmt":"2026-08-06T12:00:33","slug":"anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project","status":"publish","type":"post","link":"https:\/\/news.theck1.no\/?p=14872","title":{"rendered":"Anthropic\u2019s AI used fake identities, malware in rogue attack on GitHub project"},"content":{"rendered":"<div style=\"margin-bottom:1em; color:#666; font-size:0.9em;\">\n<strong><br \/>\n                    Jeremy Hsu<br \/>\n                <\/strong><br \/>\n &bull;<br \/>\nAugust 5, 2026\n<\/div>\n<hr\/>\n<p>Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents\u2014the most serious case arising when Anthropic\u2019s Mythos 5 model attempted to insert malicious code into an open source software application and created fake identities to deceive the human developers maintaining the project.<\/p>\n<p>The security incidents occurred during a cyber evaluation of seven leading AI models\u2019 capabilities by the AI Security Institute (AISI), a research organization within the UK government, in late July. The researchers discovered 19 instances in which \u201cAI agents took unsanctioned action on the live Internet, including cases that targeted real people and organizations,\u201d according to an <a href=\"https:\/\/www.aisi.gov.uk\/blog\/incident-report-unsanctioned-agent-behaviour-during-cyber-testing\">AISI blog post<\/a> published on August 4.<\/p>\n<p>Almost all the \u201cautonomous, unsanctioned\u201d actions came from Anthropic\u2019s Mythos 5 model, with two such actions coming from OpenAI\u2019s GPT-5.6 Sol. The AI Security Institute\u2019s security team first realized that something was amiss on the morning of July 28, when its commercial security monitoring service flagged data leaving one of the testing systems through the Tor anonymity network.<\/p>\n<p><a href=\"https:\/\/arstechnica.com\/security\/2026\/08\/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project\/\">Read full article<\/a><\/p>\n<p><a href=\"https:\/\/arstechnica.com\/security\/2026\/08\/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project\/#comments\">Comments<\/a><\/p>\n<p style=\"margin-top:1.5em;\"><a href=\"https:\/\/arstechnica.com\/security\/2026\/08\/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project\/\" target=\"_blank\" rel=\"noopener\">Read the full article &rarr;<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Jeremy Hsu &bull; August 5, 2026 Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents\u2014the most serious case arising when Anthropic\u2019s Mythos 5 model attempted to insert malicious code into an open source software application and created fake identities to deceive the human developers maintaining the project. The security incidents<\/p>\n<p class=\"more-link\"><a href=\"https:\/\/news.theck1.no\/?p=14872\" class=\"themebutton2\">READ MORE<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-14872","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence"],"_links":{"self":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts\/14872","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=14872"}],"version-history":[{"count":0,"href":"https:\/\/news.theck1.no\/index.php?rest_route=\/wp\/v2\/posts\/14872\/revisions"}],"wp:attachment":[{"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=14872"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=14872"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news.theck1.no\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=14872"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}