--- title: Securing AI agent harness files from config attacks description: Attackers are now targeting AI coding assistant configuration files (such as Claude Code's settings.json, Cursor's .cursorrules, and Copilot's instruction... canonical: https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Securing AI agent harness files from config attacks | daily.dev og:description: Attackers are now targeting AI coding assistant configuration files (such as Claude Code's settings.json, Cursor's .cursorrules, and Copilot's instruction... og:url: https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto og:image: https://api.daily.dev/og/posts/MqQeU8Uto.png og:image:alt: Securing AI agent harness files from config 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. # Securing AI agent harness files from config attacks **[Tenable Blog](https://daily.dev/sources/tenable-blog)** · 9 min read · 0 upvotes · 0 comments ## Summary Attackers are now targeting AI coding assistant configuration files (such as Claude Code's settings.json, Cursor's .cursorrules, and Copilot's instruction files) as a supply-chain attack vector. The Mini Shai-Hulud worm injects malicious SessionStart hooks into these files, causing the malware to execute silently every time a developer opens an AI coding session. A second technique injects prompt instructions directly into markdown-based rules files, exploiting the LLM's instruction-following behavior to suppress disclosure. The campaign also uses a 'clear-bomb' technique — embedding WMD-related content in payloads — to cause AI-based scanners to refuse analysis, effectively blinding automated detection. Seven defensive measures are recommended: treating harness config files as code requiring mandatory review, enforcing --ignore-scripts on package installs, flagging broad alwaysApply MDC rules, proxying LLM API traffic, treating AI scanner refusals as suspicious signals, pinning harness file hashes in CI, and rotating GitHub tokens after any untrusted npm install. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Your CLAUDE.md File Is Now a Malware Delivery Mechanism](https://daily.dev/posts/your-claude-md-file-is-now-a-malware-delivery-mechanism-1cm6dlqyv) · Medium · 1 upvotes · 0 comments - [From Assistant to Adversary: Exploiting Agentic AI Developer Tools](https://daily.dev/posts/from-assistant-to-adversary-exploiting-agentic-ai-developer-tools-dl4yjs179) · NVIDIA Developer · 2 upvotes · 0 comments - [Hackers can use 9 of the most popular AI tools to assemble massive botnets](https://daily.dev/posts/hackers-can-use-9-of-the-most-popular-ai-tools-to-assemble-massive-botnets-j8cybjfqg) · Ars Technica · 13 upvotes · 4 comments --- Tags: [#security](https://daily.dev/tags/security), [#malware](https://daily.dev/tags/malware), [#ai-coding](https://daily.dev/tags/ai-coding), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto) ```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":"Securing AI agent harness files from config attacks","url":"https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto"},"datePublished":"2026-07-21T13:03:46.044Z","dateModified":"2026-07-22T21:46:47.040Z","description":"Attackers are now targeting AI coding assistant configuration files (such as Claude Code's settings.json, Cursor's .cursorrules, and Copilot's instruction...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6a921300cecf994710654f6a51c3573d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6a921300cecf994710654f6a51c3573d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Tenable Blog","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":"Tenable Blog","logo":"https://media.daily.dev/image/upload/s--B6GAvw3H--/f_auto,q_auto/v1780213271/logos/tenable-blog?_a=BAMAMiWQ0","url":"https://daily.dev/sources/tenable-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/securing-ai-agent-harness-files-from-config-attacks-mqqeu8uto","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,malware,ai-coding,prompt-injection","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tenable Blog","item":"https://daily.dev/sources/tenable-blog"},{"@type":"ListItem","position":3,"name":"Securing AI agent harness files from config attacks"}]} ```