{"id":246980,"date":"2026-05-13T12:01:00","date_gmt":"2026-05-13T16:01:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/05\/13\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/"},"modified":"2026-05-16T01:20:16","modified_gmt":"2026-05-16T05:20:16","slug":"microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/05\/13\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/","title":{"rendered":"Microsoft, Palo Alto Networks Find Many Vulnerabilities by Using AI on Their Own Code"},"content":{"rendered":"<p><a href=\"https:\/\/www.securityweek.com\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/\">Microsoft, Palo Alto Networks Find Many Vulnerabilities by Using AI on Their Own Code<\/a><\/p>\n<p><a href=\"https:\/\/www.securityweek.com\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/\">https:\/\/www.securityweek.com\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-05-13 12:01:00<\/a><\/p>\n<p>Source Domain: <a href=\"www.securityweek.com\">www.securityweek.com<\/a><\/p>\n<p><strong>Microsoft and Palo Alto Networks have separately reported this week that they have seen significant results after turning AI on their own code to find vulnerabilities.<\/strong><\/p>\n<p>Advanced AI models such as Claude Mythos have sparked debate in the cybersecurity industry about what the vulnerability discovery landscape will look like going forward. While some organizations have confirmed that these AI models are a game-changer, others are skeptical of their actual performance.<\/p>\n<p>Microsoft said on Tuesday that more than a dozen of the 137 vulnerabilities fixed with its latest Patch Tuesday updates were found by a new AI system called MDASH (multi-model agentic scanning harness) built by its Autonomous Code Security team.<\/p>\n<p>Palo Alto Networks revealed on Wednesday that it has used Claude Mythos and other frontier AI models to conduct a deep scan of its product portfolio, which resulted in the discovery of dozens of vulnerabilities.\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-microsoft-mdash-finds-16-vulnerabilities\">Microsoft MDASH finds 16 vulnerabilities<\/h2>\n<p>Microsoft\u2019s MDASH system, which orchestrates more than 100 specialized AI agents across multiple frontier and distilled AI models, has been used to find vulnerabilities in the tech giant\u2019s own codebases.\u00a0<\/p>\n<p>MDASH is designed to run a structured pipeline that moves findings through several distinct stages: preparation, scanning, validation, deduplication, and proof construction. Different agents handle different roles: some identify candidate vulnerabilities, others argue for or against their exploitability, and a final stage attempts to construct inputs that actually trigger the bug. This multi-stage debate architecture means that a finding must withstand scrutiny before it reaches a human engineer.<\/p>\n<p><span class=\"zox-ad-label\">Advertisement. Scroll to continue reading.<\/span><\/p>\n<p>According to Microsoft, MDASH was used to discover 16 of the vulnerabilities fixed with the latest Patch Tuesday updates. Four of them were rated critical, including unauthenticated remote code execution flaws in components such as the Windows&#8230;<\/p>\n<p><a href=\"https:\/\/www.securityweek.com\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Microsoft, Palo Alto Networks Find Many Vulnerabilities by Using AI on Their Own Code https:\/\/www.securityweek.com\/microsoft-palo-alto-networks-find-many-vulnerabilities-by-using-ai-on-their-own-code\/&#8230;<\/p>\n","protected":false},"author":1,"featured_media":246981,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/www.securityweek.com\/wp-content\/uploads\/2024\/06\/AI_Weight-Models.jpg","fifu_image_alt":"","footnotes":""},"categories":[15],"tags":[26,24,27],"class_list":["post-246980","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cybersecurity","tag-ai","tag-cybersecurity","tag-vulnerability"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/246980"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=246980"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/246980\/revisions"}],"predecessor-version":[{"id":246982,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/246980\/revisions\/246982"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/246981"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=246980"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=246980"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=246980"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}