{"id":60374,"date":"2026-03-25T20:52:12","date_gmt":"2026-03-25T20:52:12","guid":{"rendered":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/"},"modified":"2026-03-25T20:52:12","modified_gmt":"2026-03-25T20:52:12","slug":"ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/","title":{"rendered":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation"},"content":{"rendered":"<p>A new service that helps coding agents stay up to date on their API calls could be dialing in a massive supply chain vulnerability.<\/p>\n<p>Two weeks ago, Andrew Ng, an AI entrepreneur and adjunct professor at Stanford, launched Context Hub, a service for supplying coding agents with API documentation.<\/p>\n<p>&#8220;Coding agents often use outdated APIs and hallucinate parameters,&#8221; Ng wrote in a <a href=\"https:\/\/www.linkedin.com\/posts\/andrewyng_im-excited-to-announce-context-hub-an-open-activity-7436817309610151936-gxvO\" rel=\"nofollow\">LinkedIn post<\/a>. &#8220;For example, when I ask Claude Code to call OpenAI&#8217;s GPT-5.2, it uses the older chat completions API instead of the newer responses API, even though the newer one has been out for a year. Context Hub solves this.&#8221;<\/p>\n<div aria-hidden=\"true\" class=\"adun\" data-pos=\"top\" data-raptor=\"condor\" data-xsm=\",fluid,mpu,dmpu,\" data-sm=\",fluid,mpu,dmpu,\" data-md=\",fluid,mpu,dmpu,\"> <noscript> <a href=\"https:\/\/pubads.g.doubleclick.net\/gampad\/jump?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\" target=\"_blank\"> <img decoding=\"async\" src=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\" alt> <\/a> <\/noscript> <\/div>\n<p>Perhaps so. But at the same time, the service appears to provide a way to dupe coding agents by simplifying software supply chain attacks: The documentation portal can be used to poison AI agents with malicious instructions.<\/p>\n<div aria-hidden=\"true\" class=\"adun\" data-pos=\"top\" data-raptor=\"falcon\" data-xmd=\",fluid,mpu,leaderboard,\" data-lg=\",fluid,mpu,leaderboard,\" data-xlg=\",fluid,billboard,superleaderboard,mpu,leaderboard,\" data-xxlg=\",fluid,billboard,superleaderboard,brandwidth,brandimpact,leaderboard,mpu,\"> <noscript> <a href=\"https:\/\/pubads.g.doubleclick.net\/gampad\/jump?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=4&amp;c=44acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0\" target=\"_blank\"> <img decoding=\"async\" src=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=4&amp;c=44acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D426raptor%3Dfalcon%26pos%3Dmid%26test%3D0\" alt> <\/a> <\/noscript> <\/div>\n<div class=\"adun_eagle_desktop_story_wrapper\">\n<div aria-hidden=\"true\" class=\"adun\" data-pos=\"mid\" data-raptor=\"eagle\" data-xxlg=\",mpu,dmpu,\"> <noscript> <a href=\"https:\/\/pubads.g.doubleclick.net\/gampad\/jump?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=3&amp;c=33acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0\" target=\"_blank\"> <img decoding=\"async\" src=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=3&amp;c=33acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0\" alt> <\/a> <\/noscript> <\/div>\n<\/p><\/div>\n<p>Mickey Shmueli, creator of an alternative curated service called lap.sh, has published <a href=\"https:\/\/github.com\/mickmicksh\/chub-supply-chain-poc\" rel=\"nofollow\">a proof-of-concept attack<\/a> that demonstrates the risk.&nbsp;<\/p>\n<p>&#8220;Context Hub delivers documentation to AI agents through an MCP server,&#8221; Shmueli wrote in an explanatory <a href=\"https:\/\/medium.com\/@mickey.shmueli\/stack-overflow-for-ai-agents-sounds-great-until-someone-poisons-the-answers-d322258095c4\" rel=\"nofollow\">blog post<\/a>. &#8220;Contributors submit docs as GitHub pull requests, maintainers merge them, and agents fetch the content on demand. The pipeline has zero content sanitization at every stage.&#8221;<\/p>\n<div aria-hidden=\"true\" class=\"adun\" data-pos=\"top\" data-raptor=\"falcon\" data-xsm=\",fluid,mpu,dmpu,\" data-sm=\",fluid,mpu,dmpu,\" data-md=\",fluid,mpu,dmpu,\"> <noscript> <a href=\"https:\/\/pubads.g.doubleclick.net\/gampad\/jump?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=4&amp;c=44acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D4%26raptor%3Dfalcon%26pos%3Dmid%26test%3D0\" target=\"_blank\"> <img decoding=\"async\" src=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=4&amp;c=44acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D426raptor%3Dfalcon%26pos%3Dmid%26test%3D0\" alt> <\/a> <\/noscript> <\/div>\n<p>It&#8217;s been known for some time in the developer community that AI models sometimes <a href=\"https:\/\/www.theregister.com\/2024\/03\/28\/ai_bots_hallucinate_software_packages\/\">hallucinate package names<\/a>, a shortcoming that security experts have shown can be exploited by uploading malicious code under the invented package name.<\/p>\n<p>Shmueli&#8217;s PoC cuts out the hallucination step by suggesting fake dependencies in documentation that coding agents then incorporate into configuration files (e.g. requirements.txt) and generated code.<\/p>\n<p>The attacker simply creates a pull request \u2013 a submitted change to the repo \u2013 and if it gets accepted, the poisoning is complete. Currently, the chance of that happening appears to be pretty good. Among 97 closed PRs, <a href=\"https:\/\/github.com\/andrewyng\/context-hub\/pulls?q=is%3Apr+is%3Aclosed+is%3Amerged\" rel=\"nofollow\">58 were merged<\/a>.<\/p>\n<p>Shmueli told <em>The Register<\/em> in an email, &#8220;The review process appears to prioritize documentation volume over security review. Doc PRs merge quickly, some by core team members themselves. I didn&#8217;t find any evidence in the GitHub repo of automated scanning for executable instructions or package references in submitted docs, though I can&#8217;t say for certain what happens internally.&#8221;<\/p>\n<p>He said he didn&#8217;t submit a PR to test how Content Hub responded &#8220;because the public record showed security contributions weren&#8217;t being engaged.&#8221; And he pointed to several open <a href=\"https:\/\/github.com\/nicepkg\/context-hub\/issues\/74\" rel=\"nofollow\">issues<\/a> and <a href=\"https:\/\/github.com\/nicepkg\/context-hub\/pull\/125\" rel=\"nofollow\">pull<\/a> <a href=\"https:\/\/github.com\/nicepkg\/context-hub\/pull\/81\" rel=\"nofollow\">requests<\/a> dealing with <a href=\"https:\/\/github.com\/nicepkg\/context-hub\/pull\/69\" rel=\"nofollow\">security concerns<\/a> as evidence.<\/p>\n<div aria-hidden=\"true\" class=\"adun\" id=\"story_eagle_xsm_sm_md_xmd_lg_xlg\" data-pos=\"mid\" data-raptor=\"eagle\" data-xsm=\",mpu,dmpu,\" data-sm=\",mpu,dmpu,\" data-md=\",mpu,dmpu,\" data-xmd=\",mpu,dmpu,\" data-lg=\",mpu,dmpu,\" data-xlg=\",mpu,dmpu,\"> <noscript> <a href=\"https:\/\/pubads.g.doubleclick.net\/gampad\/jump?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=3&amp;c=33acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0\" target=\"_blank\"> <img decoding=\"async\" src=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=3&amp;c=33acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D3%26raptor%3Deagle%26pos%3Dmid%26test%3D0\" alt> <\/a> <\/noscript> <\/div>\n<p>Ng did not immediately respond to a request for comment.<\/p>\n<p>&#8220;The agent fetches documentation from [Context Hub], reads the poisoned content, and builds the project,&#8221; Shmueli said in his post. &#8220;The response looks completely normal. Working code. Clean instructions. No warnings.&#8221;<\/p>\n<p>None of this is particularly surprising given that it&#8217;s simply a variation on the unsolved risk of AI models \u2013 <a href=\"https:\/\/www.theregister.com\/2025\/10\/09\/zenity_ai_agent_security_summit_recap\/\">indirect prompt injection<\/a>. When AI models process content, they cannot reliably distinguish between data and system instructions.<\/p>\n<p>For the PoC, two poisoned documents were created, one for Plaid Link and one for Stripe Checkout, each of which contained a fake PyPI package name.<\/p>\n<p>In 40 runs, Anthropopic&#8217;s Haiku model wrote the malicious package cited in the docs into the project&#8217;s requirement.txt file every time, without any mention of that in its output. The company&#8217;s Sonnet model did better, issuing warnings in 48 percent of the runs (19\/40) but still wrote the malicious library into requirements.txt 53 percent of the time (21\/40). The AI biz&#8217;s top-of-the-line Opus model did better still, issuing warnings 75 percent of the time (30\/40) and didn&#8217;t end up writing the bad dependency to the requirements.txt file or code.<\/p>\n<p>Shmueli said Opus &#8220;is trained better, on more packages, and it&#8217;s more sophisticated.&#8221;<\/p>\n<p>So while higher-end commercial models appear to be capable of catching fabulated dependencies, the problem is broader than just Context Hub. According to Shmueli, all the other systems for making community-authored documentation available to AI models <a href=\"https:\/\/github.com\/mickmicksh\/chub-supply-chain-poc\/blob\/main\/alternatives-comparison.md\" rel=\"nofollow\">fall short when it comes to content sanitization<\/a>.&nbsp;<\/p>\n<p>Exposure to untrusted content is one of the three risks cited by developer Simon Willison in his <a href=\"https:\/\/simonwillison.net\/2025\/Jun\/16\/the-lethal-trifecta\/\" rel=\"nofollow\">lethal trifecta AI security model<\/a>. So given unvetted documentation as the status quo, you&#8217;d be well-advised to ensure either that your AI agent has no network access, or at the very least no access to private data. \u00ae<\/p>\n<p> READ MORE <a href=\"https:\/\/go.theregister.com\/feed\/www.theregister.com\/2026\/03\/25\/ai_agents_supply_chain_attack_context_hub\/\">HERE<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A proof-of-concept attack on Context Hub suggests there&#8217;s not much content santization A new service that helps coding agents stay up to date on their API calls could be dialing in a massive supply chain vulnerability.\u2026 READ MORE HERE&#8230;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_layout":"default_layout","footnotes":""},"categories":[63],"tags":[],"class_list":["post-60374","post","type-post","status-publish","format-standard","hentry","category-the-register"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News<\/title>\n<meta name=\"description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News\" \/>\n<meta property=\"og:description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\" \/>\n<meta property=\"og:site_name\" content=\"ThreatsHub Cybersecurity News\" \/>\n<meta property=\"article:published_time\" content=\"2026-03-25T20:52:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\" \/>\n<meta name=\"author\" content=\"TH Author\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@threatshub\" \/>\n<meta name=\"twitter:site\" content=\"@threatshub\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"TH Author\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\"},\"author\":{\"name\":\"TH Author\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476\"},\"headline\":\"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation\",\"datePublished\":\"2026-03-25T20:52:12+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\"},\"wordCount\":735,\"publisher\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\",\"articleSection\":[\"The Register\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\",\"url\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\",\"name\":\"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News\",\"isPartOf\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\",\"datePublished\":\"2026-03-25T20:52:12+00:00\",\"description\":\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage\",\"url\":\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\",\"contentUrl\":\"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.threatshub.org\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#website\",\"url\":\"https:\/\/www.threatshub.org\/blog\/\",\"name\":\"ThreatsHub Cybersecurity News\",\"description\":\"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform\",\"publisher\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/#organization\"},\"alternateName\":\"Threatshub.org\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.threatshub.org\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#organization\",\"name\":\"ThreatsHub.org\",\"alternateName\":\"Threatshub.org\",\"url\":\"https:\/\/www.threatshub.org\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg\",\"contentUrl\":\"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg\",\"width\":432,\"height\":435,\"caption\":\"ThreatsHub.org\"},\"image\":{\"@id\":\"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/threatshub\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476\",\"name\":\"TH Author\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"caption\":\"TH Author\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/","og_locale":"en_US","og_type":"article","og_title":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News","og_description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","og_url":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/","og_site_name":"ThreatsHub Cybersecurity News","article_published_time":"2026-03-25T20:52:12+00:00","og_image":[{"url":"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0","type":"","width":"","height":""}],"author":"TH Author","twitter_card":"summary_large_image","twitter_creator":"@threatshub","twitter_site":"@threatshub","twitter_misc":{"Written by":"TH Author","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#article","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/"},"author":{"name":"TH Author","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476"},"headline":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation","datePublished":"2026-03-25T20:52:12+00:00","mainEntityOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/"},"wordCount":735,"publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage"},"thumbnailUrl":"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0","articleSection":["The Register"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/","url":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/","name":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation 2026 | ThreatsHub Cybersecurity News","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage"},"thumbnailUrl":"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0","datePublished":"2026-03-25T20:52:12+00:00","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","breadcrumb":{"@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#primaryimage","url":"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0","contentUrl":"https:\/\/pubads.g.doubleclick.net\/gampad\/ad?co=1&amp;iu=\/6978\/reg_security\/front&amp;sz=300x50%7C300x100%7C300x250%7C300x251%7C300x252%7C300x600%7C300x601&amp;tile=2&amp;c=2acR1bLGiSPGaHWyIOYRP1QAAAYs&amp;t=ct%3Dns%26unitnum%3D2%26raptor%3Dcondor%26pos%3Dtop%26test%3D0"},{"@type":"BreadcrumbList","@id":"https:\/\/www.threatshub.org\/blog\/ai-supply-chain-attacks-dont-even-require-malwarejust-post-poisoned-documentation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.threatshub.org\/blog\/"},{"@type":"ListItem","position":2,"name":"AI supply chain attacks don\u2019t even require malware\u2026just post poisoned documentation"}]},{"@type":"WebSite","@id":"https:\/\/www.threatshub.org\/blog\/#website","url":"https:\/\/www.threatshub.org\/blog\/","name":"ThreatsHub Cybersecurity News","description":"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform","publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"alternateName":"Threatshub.org","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.threatshub.org\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.threatshub.org\/blog\/#organization","name":"ThreatsHub.org","alternateName":"Threatshub.org","url":"https:\/\/www.threatshub.org\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","contentUrl":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","width":432,"height":435,"caption":"ThreatsHub.org"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/threatshub"]},{"@type":"Person","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476","name":"TH Author","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","caption":"TH Author"}}]}},"_links":{"self":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/60374","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/comments?post=60374"}],"version-history":[{"count":0,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/60374\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/media?parent=60374"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/categories?post=60374"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/tags?post=60374"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}