--- title: How AI Agents Expand the Software Supply Chain Attack... description: Socket founder Feross Aboukhadijeh's AI Council 2026 talk examines how AI coding agents are reshaping the software supply chain threat model. Agents now select... canonical: https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How AI Agents Expand the Software Supply Chain Attack Surface | daily.dev og:description: Socket founder Feross Aboukhadijeh's AI Council 2026 talk examines how AI coding agents are reshaping the software supply chain threat model. Agents now select... og:url: https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06 og:image: https://api.daily.dev/og/posts/XTel0ZH06.png og:image:alt: How AI Agents Expand the Software Supply Chain Attack Surface 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. # How AI Agents Expand the Software Supply Chain Attack Surface **[Socket](https://daily.dev/sources/socketdev)** · 2 min read · 1 upvotes · 0 comments ## Summary Socket founder Feross Aboukhadijeh's AI Council 2026 talk examines how AI coding agents are reshaping the software supply chain threat model. Agents now select dependencies, connect to MCP servers, install skills, and run code with developer credentials, often without human review, straining security infrastructure built around human trust decisions. The talk walks through 2026 supply chain attacks involving Axios, TanStack, and Trivy, covering compromised maintainers, malicious transitive dependencies, prompt injection, and risks in MCP servers, agent skills, and IDE extensions. It closes with a more optimistic view of AI helping defenders analyze code and prioritize vulnerabilities. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can AI coding agents introduce software supply chain security risks? AI coding agents can autonomously select dependencies, connect to MCP servers, install skills, and execute code using a developer's own credentials, often without human review. This removes the human trust-decision step that existing security tooling assumes exists, so malicious packages, compromised maintainers, and prompt injection attacks can reach developers through their agents rather than being caught before installation. _Developers hardening agent-driven workflows can track emerging supply chain risks like these on daily.dev._ ### What real-world supply chain attacks happened involving packages like Axios, TanStack, or Trivy? Attackers compromised maintainers and used malicious transitive dependencies, prompt injection, and trusted development tools to target both developers and their AI agents in incidents involving Axios, TanStack, and Trivy. These cases illustrate how trusted open source packages and toolchains became vectors for reaching automated coding agents, not just human developers. _Teams auditing dependencies for similar compromises can follow ongoing supply chain incidents on daily.dev._ ## Similar posts on daily.dev - [The software supply chain is the new battlefield. AI just changed the rules.](https://daily.dev/posts/the-software-supply-chain-is-the-new-battlefield-ai-just-changed-the-rules--mtuqueyhv) · The New Stack · 1 upvotes · 0 comments - [The New Security Risks of Agentic Development](https://daily.dev/posts/the-new-security-risks-of-agentic-development-rjskp1wg4) · Snyk · 1 upvotes · 0 comments - [Securing Agents & AI Supply Chain with Cisco AI Defense](https://daily.dev/posts/securing-agents-ai-supply-chain-with-cisco-ai-defense-iugqrwlli) · Cisco · 1 upvotes · 0 comments - [\[Webinar\] Securing Agentic AI: From MCPs and Tool Access to Shadow API Key Sprawl](https://daily.dev/posts/webinar-securing-agentic-ai-from-mcps-and-tool-access-to-shadow-api-key-sprawl-hokzzedlq) · The Hacker News · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#open-source](https://daily.dev/tags/open-source), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp) [View this post on daily.dev](https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06) ```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":"How AI Agents Expand the Software Supply Chain Attack Surface","url":"https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06"},"datePublished":"2026-08-17T05:26:11.561Z","dateModified":"2026-09-13T20:45:50.744Z","description":"Socket founder Feross Aboukhadijeh's AI Council 2026 talk examines how AI coding agents are reshaping the software supply chain threat model. Agents now select...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7a9ae0d966df122389c5c77a4078181f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/7a9ae0d966df122389c5c77a4078181f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Socket","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":"Socket","logo":"https://media.daily.dev/image/upload/s---oEn9czC--/f_auto/v1716187892/logos/socketdev","url":"https://daily.dev/sources/socketdev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,open-source,ai-agents,mcp","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Socket","item":"https://daily.dev/sources/socketdev"},{"@type":"ListItem","position":3,"name":"How AI Agents Expand the Software Supply Chain Attack Surface"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-ai-agents-expand-the-software-supply-chain-attack-surface-xtel0zh06#faq","mainEntity":[{"@type":"Question","name":"How can AI coding agents introduce software supply chain security risks?","acceptedAnswer":{"@type":"Answer","text":"AI coding agents can autonomously select dependencies, connect to MCP servers, install skills, and execute code using a developer's own credentials, often without human review. This removes the human trust-decision step that existing security tooling assumes exists, so malicious packages, compromised maintainers, and prompt injection attacks can reach developers through their agents rather than being caught before installation. Developers hardening agent-driven workflows can track emerging supply chain risks like these on daily.dev."}},{"@type":"Question","name":"What real-world supply chain attacks happened involving packages like Axios, TanStack, or Trivy?","acceptedAnswer":{"@type":"Answer","text":"Attackers compromised maintainers and used malicious transitive dependencies, prompt injection, and trusted development tools to target both developers and their AI agents in incidents involving Axios, TanStack, and Trivy. These cases illustrate how trusted open source packages and toolchains became vectors for reaching automated coding agents, not just human developers. Teams auditing dependencies for similar compromises can follow ongoing supply chain incidents on daily.dev."}}]} ```