--- title: Prompt-Jacking: The Rise of a New Supply Chain Risk -... description: Security researchers from Hidden Layer demonstrate a range of attacks targeting AI coding agents and agentic systems, collectively framed as 'prompt-jacking.'... canonical: https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung | daily.dev og:description: Security researchers from Hidden Layer demonstrate a range of attacks targeting AI coding agents and agentic systems, collectively framed as 'prompt-jacking.'... og:url: https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen og:image: https://api.daily.dev/og/posts/1eYiWmAEN.png og:image:alt: Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung 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. # Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung **[NDC Conferences](https://daily.dev/sources/ndc)** · 61 min read · 0 upvotes · 0 comments ## Summary Security researchers from Hidden Layer demonstrate a range of attacks targeting AI coding agents and agentic systems, collectively framed as 'prompt-jacking.' Key attack vectors include: hidden instructions in raw markdown README files (invisible in rendered views) exploiting Cursor's command injection CVE to exfiltrate SSH keys; user-agent-based prompt injection where malicious websites serve different content to LLM scrapers than to humans; Mermaid diagram rendering used to exfiltrate secrets via image requests; wkhtmltopdf (WeasyPrint) local file attachment vulnerabilities; control sequence injection attacks against Open Web UI's RAG system; MCP tool name collision attacks where a malicious server overrides legitimate tool definitions; and skill/agent file name-description injection that places attacker instructions directly into the system prompt. The talk also covers instruction hierarchy, control tokens vs. control sequences, and how agentic design decisions undermine model-level security training. Defensive recommendations include sanitizing control sequences from user/tool inputs, auditing skill names and descriptions, and proper data/control plane separation. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Prompt Injection Isn’t Just a Chat Problem — It’s a DevOps Threat](https://daily.dev/posts/prompt-injection-isn-t-just-a-chat-problem-it-s-a-devops-threat-42ohpini3) · DevOps.com · 0 upvotes · 0 comments - [The Prompt Injection Peril and Why AI Agents Are Your Network’s Newest Vulnerability](https://daily.dev/posts/the-prompt-injection-peril-and-why-ai-agents-are-your-network-s-newest-vulnerability-vu0delvbu) · Security Boulevard · 1 upvotes · 0 comments - [Hiding Prompts in Plain Sight: A New AI Security Risk](https://daily.dev/posts/hiding-prompts-in-plain-sight-a-new-ai-security-risk-mzblzfejg) · Auth0 · 1 upvotes · 0 comments - [Security for AI Agents: Prompt Injection Is Only the Beginning](https://daily.dev/posts/security-for-ai-agents-prompt-injection-is-only-the-beginning-4pgyeh5xl) · Medium · 2 upvotes · 1 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#ai-security](https://daily.dev/tags/ai-security), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen) ```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":"Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung","url":"https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen"},"datePublished":"2026-07-31T12:10:00.933Z","dateModified":"2026-08-01T00:15:46.754Z","description":"Security researchers from Hidden Layer demonstrate a range of attacks targeting AI coding agents and agentic systems, collectively framed as 'prompt-jacking.'...","image":"https://i.ytimg.com/vi/SsTtp_Nrmn4/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/SsTtp_Nrmn4/sddefault.jpg","isAccessibleForFree":true,"articleSection":"NDC Conferences","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":"NDC Conferences","logo":"https://media.daily.dev/image/upload/s--SiIyojEj--/f_auto/v1748760369/logos/ndc","url":"https://daily.dev/sources/ndc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/prompt-jacking-the-rise-of-a-new-supply-chain-risk---kasimir-schulz-kenneth-yeung-1eyiwmaen","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,mcp,ai-security,prompt-injection","timeRequired":"PT61M","video":{"@type":"VideoObject","name":"Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung","description":"Security researchers from Hidden Layer demonstrate a range of attacks targeting AI coding agents and agentic systems, collectively framed as 'prompt-jacking.'...","thumbnailUrl":"https://i.ytimg.com/vi/SsTtp_Nrmn4/sddefault.jpg","uploadDate":"2026-07-31T12:10:00.933Z","duration":"PT61M","url":"https://api.daily.dev/r/1eYiWmAEN","embedUrl":"https://www.youtube.com/embed/SsTtp_Nrmn4"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NDC Conferences","item":"https://daily.dev/sources/ndc"},{"@type":"ListItem","position":3,"name":"Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung"}]} ```