--- title: Giving a local LLM full VM access showed me why we need... description: An experiment giving a local LLM full access to a WSL2 VM via the OpenClaw harness revealed practical risks of agentic AI. The LLM was tasked with installing... canonical: https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Giving a local LLM full VM access showed me why we need better AI guardrails | daily.dev og:description: An experiment giving a local LLM full access to a WSL2 VM via the OpenClaw harness revealed practical risks of agentic AI. The LLM was tasked with installing... og:url: https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq og:image: https://api.daily.dev/og/posts/ZDLYUQtFQ.png og:image:alt: Giving a local LLM full VM access showed me why we need better AI guardrails 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. # Giving a local LLM full VM access showed me why we need better AI guardrails **[XDA Developers](https://daily.dev/sources/xda-developers)** · 3 min read · 1 upvotes · 0 comments ## Summary An experiment giving a local LLM full access to a WSL2 VM via the OpenClaw harness revealed practical risks of agentic AI. The LLM was tasked with installing persistent memory tools and switching to a vLLM/Gemma 4 endpoint, but repeatedly lied about completing tasks and failed to execute reliably. The experience reinforced concerns about AI guardrails — not because the AI went rogue, but because its unpredictability and hallucinations make it unsafe to run on systems with real personal data. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [I let two local LLMs fight over how to optimize a Linux VM, and they destroyed it instead](https://daily.dev/posts/i-let-two-local-llms-fight-over-how-to-optimize-a-linux-vm-and-they-destroyed-it-instead-mvuaz51pc) · XDA Developers · 2 upvotes · 1 comments - [Trying to self-host LLMs made me realize local AI has a friction problem, not a quality problem](https://daily.dev/posts/trying-to-self-host-llms-made-me-realize-local-ai-has-a-friction-problem-not-a-quality-problem-ni4ffneoq) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#infrastructure](https://daily.dev/tags/infrastructure), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-safety](https://daily.dev/tags/ai-safety), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq) ```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":"Giving a local LLM full VM access showed me why we need better AI guardrails","url":"https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq"},"datePublished":"2026-04-27T10:04:46.066Z","dateModified":"2026-04-27T10:05:09.837Z","description":"An experiment giving a local LLM full access to a WSL2 VM via the OpenClaw harness revealed practical risks of agentic AI. The LLM was tasked with installing...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bd14a0025cb89db38e49012721a499e8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bd14a0025cb89db38e49012721a499e8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/giving-a-local-llm-full-vm-access-showed-me-why-we-need-better-ai-guardrails-zdlyuqtfq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"infrastructure,llm,ai-agents,ai-safety,prompt-injection","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"Giving a local LLM full VM access showed me why we need better AI guardrails"}]} ```