--- title: AI-Discovered Security Flaws Are Not Yet Translating... description: VulnCheck researcher Patrick Garrity analyzed data from Anthropic's Claude Mythos and the Berkeley Vulnerability Research Initiative, finding that only 1.3% of... canonical: https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI-Discovered Security Flaws Are Not Yet Translating into More Exploitation | daily.dev og:description: VulnCheck researcher Patrick Garrity analyzed data from Anthropic's Claude Mythos and the Berkeley Vulnerability Research Initiative, finding that only 1.3% of... og:url: https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7 og:image: https://api.daily.dev/og/posts/pyvaTUet7.png og:image:alt: AI-Discovered Security Flaws Are Not Yet Translating into More Exploitation 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. # AI-Discovered Security Flaws Are Not Yet Translating into More Exploitation **[Security Boulevard](https://daily.dev/sources/securityboulevard)** · 5 min read · 0 upvotes · 0 comments ## Summary VulnCheck researcher Patrick Garrity analyzed data from Anthropic's Claude Mythos and the Berkeley Vulnerability Research Initiative, finding that only 1.3% of 1,061 AI-discovered vulnerabilities have been exploited in the wild — a rate no higher than traditionally discovered flaws. Despite industry fears that frontier AI models like Mythos and OpenAI's equivalents would trigger a wave of attacks, the current evidence suggests defenders are benefiting more than attackers. Of 23,019 findings from Anthropic's Project Glasswing, only 126 became CVEs and just one was confirmed exploited. Researchers caution the risk remains real as more powerful models emerge, but say the threat is currently overhyped relative to actual impact. Meanwhile, industry alliances like Nvidia's Open Secure AI Alliance and ExtraHop's Agentic SOC Alliance are forming in response to AI-driven security concerns. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [AI finds 10,000 vulnerabilities. China is copying the models.](https://daily.dev/posts/ai-finds-10-000-vulnerabilities-china-is-copying-the-models--nhkllgfpd) · The Next Web · 1 upvotes · 0 comments - [How Mythos Signals Cybersecurity Disruption](https://daily.dev/posts/how-mythos-signals-cybersecurity-disruption-ng2ydu97n) · Security Boulevard · 0 upvotes · 0 comments --- Tags: [#claude](https://daily.dev/tags/claude), [#ai-security](https://daily.dev/tags/ai-security) [View this post on daily.dev](https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7) ```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":"AI-Discovered Security Flaws Are Not Yet Translating into More Exploitation","url":"https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7"},"datePublished":"2026-07-28T20:24:47.575Z","dateModified":"2026-07-31T13:23:18.662Z","description":"VulnCheck researcher Patrick Garrity analyzed data from Anthropic's Claude Mythos and the Berkeley Vulnerability Research Initiative, finding that only 1.3% of...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/20d0e7ba7d31da41b67710f79269758b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/20d0e7ba7d31da41b67710f79269758b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Security Boulevard","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":"Security Boulevard","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3613c832180040de8d85bb29f74395be","url":"https://daily.dev/sources/securityboulevard"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-discovered-security-flaws-are-not-yet-translating-into-more-exploitation-pyvatuet7","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"claude,ai-security","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Security Boulevard","item":"https://daily.dev/sources/securityboulevard"},{"@type":"ListItem","position":3,"name":"AI-Discovered Security Flaws Are Not Yet Translating into More Exploitation"}]} ```