--- title: Layered sandboxing for AI agents: OpenShift and OpenShell description: AI coding agents require shell access, file I/O, and network calls — the same capability profile as a compromised workload. No single sandbox technology covers... canonical: https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Layered sandboxing for AI agents: OpenShift and OpenShell | daily.dev og:description: AI coding agents require shell access, file I/O, and network calls — the same capability profile as a compromised workload. No single sandbox technology covers... og:url: https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t og:image: https://api.daily.dev/og/posts/LEkDK6l8t.png og:image:alt: Layered sandboxing for AI agents: OpenShift and OpenShell 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. # Layered sandboxing for AI agents: OpenShift and OpenShell **[Red Hat Developer](https://daily.dev/sources/rhdev)** · 9 min read · 0 upvotes · 0 comments ## Summary AI coding agents require shell access, file I/O, and network calls — the same capability profile as a compromised workload. No single sandbox technology covers the full threat surface. This post explains how combining NVIDIA OpenShell (application-layer egress filtering, filesystem isolation via Linux Landlock) with Red Hat OpenShift sandboxed containers (Kata Containers, hardware VM-level kernel isolation) creates complementary defense layers. OpenShell blocks data exfiltration and prompt injection attacks at the network proxy level, while Kata Containers prevents kernel exploits and cross-container page cache corruption by giving each pod its own guest kernel. Testing on OpenShift 4.21 with two real attacks — a prompt injection exfiltration and CVE-2026-31431 (a page cache corruption exploit) — showed that only the dual-protected pod blocked both. Each attack succeeded against the pod missing its corresponding protection layer. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Why your AI agent needs two sandboxes: Benchmark data](https://daily.dev/posts/why-your-ai-agent-needs-two-sandboxes-benchmark-data-zexdlcp4n) · Red Hat Developer · 0 upvotes · 0 comments - [Securing Enterprise Agents with NVIDIA OpenShell and Cisco AI Defense](https://daily.dev/posts/securing-enterprise-agents-with-nvidia-openshell-and-cisco-ai-defense-ptgb4m0oe) · Cisco · 1 upvotes · 0 comments - [Jensen Huang and Bill McDermott bet on OpenShell to secure enterprise AI agents](https://daily.dev/posts/jensen-huang-and-bill-mcdermott-bet-on-openshell-to-secure-enterprise-ai-agents-4oljbl2lx) · The New Stack · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#containers](https://daily.dev/tags/containers), [#openshift](https://daily.dev/tags/openshift) [View this post on daily.dev](https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t) ```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":"Layered sandboxing for AI agents: OpenShift and OpenShell","url":"https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t"},"datePublished":"2026-07-16T07:07:03.807Z","dateModified":"2026-07-16T07:07:26.212Z","description":"AI coding agents require shell access, file I/O, and network calls — the same capability profile as a compromised workload. No single sandbox technology covers...","image":"https://media.daily.dev/image/upload/s--foaA6JGU--/f_auto/v1722860399/public/Placeholder%2004","thumbnailUrl":"https://media.daily.dev/image/upload/s--foaA6JGU--/f_auto/v1722860399/public/Placeholder%2004","isAccessibleForFree":true,"articleSection":"Red Hat Developer","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":"Red Hat Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/2a8895f3216c4900bdc455585a4ad3e4","url":"https://daily.dev/sources/rhdev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/layered-sandboxing-for-ai-agents-openshift-and-openshell-lekdk6l8t","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,containers,openshift","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Red Hat Developer","item":"https://daily.dev/sources/rhdev"},{"@type":"ListItem","position":3,"name":"Layered sandboxing for AI agents: OpenShift and OpenShell"}]} ```