--- title: Purpose-built model for leaked secret detection | daily.dev description: GitHub is rolling out a purpose-built AI model for detecting leaked secrets across secret scanning alerts, push protection, and Copilot security reviews,... canonical: https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Purpose-built model for leaked secret detection | daily.dev og:description: GitHub is rolling out a purpose-built AI model for detecting leaked secrets across secret scanning alerts, push protection, and Copilot security reviews,... og:url: https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c og:image: https://api.daily.dev/og/posts/LduAVgP6C.png og:image:alt: Purpose-built model for leaked secret detection 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. # Purpose-built model for leaked secret detection **[GitHub Changelog](https://daily.dev/sources/github_updates)** · 6 min read · 0 upvotes · 0 comments ## Summary GitHub is rolling out a purpose-built AI model for detecting leaked secrets across secret scanning alerts, push protection, and Copilot security reviews, including passwords without recognizable token formats. AI-detected secret alerts are automatically upgraded to the new model at no extra charge for GHSP/GHAS customers, while new opt-in checks for push protection and the Copilot /security-review command will consume AI Credits once billing begins in the coming weeks. The model is also coming to GitHub Enterprise Server 3.23 in public preview. Administrators can set budgets and disable the new capabilities by policy. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does GitHub's new AI model for secret detection actually do differently from before? It reads surrounding code context to identify likely credentials, including passwords that lack a recognizable token format, without generating any code or prose itself. Customers with AI-detected Password alerts were automatically upgraded to this fine-tuned model at no additional charge. It also powers new opt-in checks in push protection and the Copilot /security-review command. _Teams tightening secret-scanning coverage can track rollout details like this on daily.dev._ ### Will GitHub's new AI secret detection in push protection cost extra? Yes, the opt-in AI-detected secrets check in push protection and the Copilot /security-review secret classifier checks will consume GitHub AI Credits, billed under the Secret Protection AI Credits SKU, once billing begins in the coming weeks. Existing AI-detected secret alert scans remain included in GHSP and GHAS at no additional charge, since they are a separate, non-credit-consuming feature. _Anyone budgeting AI Credit usage for security tooling can follow pricing changes like this on daily.dev._ ### Is GitHub's new AI secret detection model coming to GitHub Enterprise Server? Yes, it is planned for GitHub Enterprise Server 3.23 in public preview, included with an enterprise's existing GHSP or GHAS purchase at no additional charge. Push protection and the Copilot /security-review command are not part of this Server release, so those features remain limited to GitHub Enterprise Cloud and Team plans. _Admins planning GHES upgrades can keep tabs on feature rollouts like this via daily.dev._ ## Similar posts on daily.dev - [GitHub expands application security coverage with AI‑powered detections](https://daily.dev/posts/github-expands-application-security-coverage-with-ai-powered-detections-ealox7aer) · GitHub Blog · 0 upvotes · 0 comments - [GitGuardian Reports an 81% Surge of AI-Service Leaks as 29M Secrets Hit Public GitHub](https://daily.dev/posts/gitguardian-reports-an-81-surge-of-ai-service-leaks-as-29m-secrets-hit-public-github-1np8gniww) · Security Boulevard · 0 upvotes · 0 comments - [Generative AI Security: Catch Secrets in Your AI Gateway](https://daily.dev/posts/generative-ai-security-catch-secrets-in-your-ai-gateway-rsc0fcpvk) · GitGuardian · 0 upvotes · 0 comments - [Secret scanning with GitHub MCP Server is now generally available](https://daily.dev/posts/secret-scanning-with-github-mcp-server-is-now-generally-available-lenk8fgbw) · GitHub Changelog · 1 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#cicd](https://daily.dev/tags/cicd), [#appsec](https://daily.dev/tags/appsec) [View this post on daily.dev](https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c) ```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":"Purpose-built model for leaked secret detection","url":"https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c"},"datePublished":"2026-10-07T18:13:09.973Z","dateModified":"2026-10-13T18:54:40.511Z","description":"GitHub is rolling out a purpose-built AI model for detecting leaked secrets across secret scanning alerts, push protection, and Copilot security reviews,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8754bd2bde7fe0247e730ac8a79bd524?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8754bd2bde7fe0247e730ac8a79bd524?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"GitHub Changelog","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":"GitHub Changelog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/15004b7835da4d89b02b115871f0f6dc","url":"https://daily.dev/sources/github_updates"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,cicd,appsec","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"GitHub Changelog","item":"https://daily.dev/sources/github_updates"},{"@type":"ListItem","position":3,"name":"Purpose-built model for leaked secret detection"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/purpose-built-model-for-leaked-secret-detection-lduavgp6c#faq","mainEntity":[{"@type":"Question","name":"What does GitHub's new AI model for secret detection actually do differently from before?","acceptedAnswer":{"@type":"Answer","text":"It reads surrounding code context to identify likely credentials, including passwords that lack a recognizable token format, without generating any code or prose itself. Customers with AI-detected Password alerts were automatically upgraded to this fine-tuned model at no additional charge. It also powers new opt-in checks in push protection and the Copilot /security-review command. Teams tightening secret-scanning coverage can track rollout details like this on daily.dev."}},{"@type":"Question","name":"Will GitHub's new AI secret detection in push protection cost extra?","acceptedAnswer":{"@type":"Answer","text":"Yes, the opt-in AI-detected secrets check in push protection and the Copilot /security-review secret classifier checks will consume GitHub AI Credits, billed under the Secret Protection AI Credits SKU, once billing begins in the coming weeks. Existing AI-detected secret alert scans remain included in GHSP and GHAS at no additional charge, since they are a separate, non-credit-consuming feature. Anyone budgeting AI Credit usage for security tooling can follow pricing changes like this on daily.dev."}},{"@type":"Question","name":"Is GitHub's new AI secret detection model coming to GitHub Enterprise Server?","acceptedAnswer":{"@type":"Answer","text":"Yes, it is planned for GitHub Enterprise Server 3.23 in public preview, included with an enterprise's existing GHSP or GHAS purchase at no additional charge. Push protection and the Copilot /security-review command are not part of this Server release, so those features remain limited to GitHub Enterprise Cloud and Team plans. Admins planning GHES upgrades can keep tabs on feature rollouts like this via daily.dev."}}]} ```