--- title: Forescout Research Tests Whether AI Can Create PLC Attacks description: Forescout's Vedere Labs research tested whether AI could port a remote code execution exploit between two WAGO PLC models, finding that AI succeeded but only... canonical: https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Forescout Research Tests Whether AI Can Create PLC Attacks | daily.dev og:description: Forescout's Vedere Labs research tested whether AI could port a remote code execution exploit between two WAGO PLC models, finding that AI succeeded but only... og:url: https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg og:image: https://api.daily.dev/og/posts/vSgmce3wG.png og:image:alt: Forescout Research Tests Whether AI Can Create PLC Attacks 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. # Forescout Research Tests Whether AI Can Create PLC Attacks **[IT Security Guru](https://daily.dev/sources/itsecurityguru)** · 3 min read · 0 upvotes · 0 comments ## Summary Forescout's Vedere Labs research tested whether AI could port a remote code execution exploit between two WAGO PLC models, finding that AI succeeded but only with substantial human guidance. Building the working exploit took over 8 hours and cost $535.74 in API tokens, with researchers steering the AI past false leads and dead ends. Once initial code execution was achieved, AI rapidly produced multiple working network payloads within minutes. An attempt to develop a command-and-control implant permanently bricked the PLC, underscoring risks of AI operating against physical hardware. Researchers conclude AI cannot yet autonomously develop sophisticated PLC attacks, but warn that as models improve, the cost and expertise barrier for exploiting industrial devices could fall significantly. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can AI autonomously develop exploits for industrial PLCs today? Not reliably on its own. Forescout's Vedere Labs found AI could help port a remote code execution exploit between two WAGO PLC models, but only with extensive human guidance through false leads and dead ends, taking over 8 hours and 32 minutes and costing $535.74 in API tokens to complete. _Security teams tracking AI's growing offensive capabilities can follow OT threat research on daily.dev._ ### What happened when researchers used AI to build a command-and-control implant on a PLC? The PLC was permanently bricked. During Forescout's Vedere Labs experiment, attempting to have AI develop a command-and-control implant for the device caused irreversible damage, illustrating the physical risk of letting AI operate against embedded industrial hardware rather than software targets. _Engineers weighing AI automation risks in OT environments can keep up with such findings on daily.dev._ ## Similar posts on daily.dev - [What happens when AI models take aim at ICS exploits](https://daily.dev/posts/what-happens-when-ai-models-take-aim-at-ics-exploits-jv2hqkdns) · CSO Online · 0 upvotes · 0 comments - [Why your AI strategy stops where the PLC starts: Hard lessons from the OT frontlines](https://daily.dev/posts/why-your-ai-strategy-stops-where-the-plc-starts-hard-lessons-from-the-ot-frontlines-abqv2z1zq) · CSO Online · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-security](https://daily.dev/tags/ai-security) [View this post on daily.dev](https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg) ```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":"Forescout Research Tests Whether AI Can Create PLC Attacks","url":"https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg"},"datePublished":"2026-09-01T20:40:56.897Z","dateModified":"2026-09-01T20:41:21.750Z","description":"Forescout's Vedere Labs research tested whether AI could port a remote code execution exploit between two WAGO PLC models, finding that AI succeeded but only...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d82e10d14a4f077850fff388a9f82e03?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d82e10d14a4f077850fff388a9f82e03?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"IT Security Guru","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":"IT Security Guru","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/ae9fe7d07c814192b35f86ad698fb374","url":"https://daily.dev/sources/itsecurityguru"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-security","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"IT Security Guru","item":"https://daily.dev/sources/itsecurityguru"},{"@type":"ListItem","position":3,"name":"Forescout Research Tests Whether AI Can Create PLC Attacks"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/forescout-research-tests-whether-ai-can-create-plc-attacks-vsgmce3wg#faq","mainEntity":[{"@type":"Question","name":"Can AI autonomously develop exploits for industrial PLCs today?","acceptedAnswer":{"@type":"Answer","text":"Not reliably on its own. Forescout's Vedere Labs found AI could help port a remote code execution exploit between two WAGO PLC models, but only with extensive human guidance through false leads and dead ends, taking over 8 hours and 32 minutes and costing $535.74 in API tokens to complete. Security teams tracking AI's growing offensive capabilities can follow OT threat research on daily.dev."}},{"@type":"Question","name":"What happened when researchers used AI to build a command-and-control implant on a PLC?","acceptedAnswer":{"@type":"Answer","text":"The PLC was permanently bricked. During Forescout's Vedere Labs experiment, attempting to have AI develop a command-and-control implant for the device caused irreversible damage, illustrating the physical risk of letting AI operate against embedded industrial hardware rather than software targets. Engineers weighing AI automation risks in OT environments can keep up with such findings on daily.dev."}}]} ```