--- title: My Agentic Trust Issues: From Prompt Injection to... description: Pillar Security researchers discovered a CVSS 10 critical vulnerability (TrustIssues) in Google's AI-powered GitHub Actions workflows. By opening a public... canonical: https://daily.dev/posts/wd82ycspd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli | daily.dev og:description: Pillar Security researchers discovered a CVSS 10 critical vulnerability (TrustIssues) in Google's AI-powered GitHub Actions workflows. By opening a public... og:url: https://daily.dev/posts/wd82ycspd og:image: https://api.daily.dev/og/posts/WD82YcSpd.png og:image:alt: Post cover image 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. # My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli **[Information Security Things](https://daily.dev/sources/securitythings)** · [@nosashandy](https://daily.dev/nosashandy) · 0 upvotes · 0 comments ## Summary Pillar Security researchers discovered a CVSS 10 critical vulnerability (TrustIssues) in Google's AI-powered GitHub Actions workflows. By opening a public GitHub issue with a hidden prompt injection payload, an attacker could hijack a Gemini CLI agent running in --yolo mode to exfiltrate workflow secrets and Git credentials stored on disk, ultimately achieving full supply-chain compromise of the gemini-cli repository (101K+ stars). The attack exploited the 'lethal trifecta': the agent had access to private data (secrets/tokens), was exposed to untrusted content (issue bodies), and could communicate externally. Google patched the issue within days (gemini-cli 0.39.1), enforcing tool allowlists even under --yolo mode. Recommendations include disabling credential persistence in actions/checkout, auditing AI agent triggers, and treating prompt injection as a privilege escalation problem rather than a prompt-hardening problem. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Cybersecurity Researchers Uncover Flaw in Google AI Coding Tool](https://daily.dev/posts/cybersecurity-researchers-uncover-flaw-in-google-ai-coding-tool-38fhs0zr4) · DevOps.com · 1 upvotes · 0 comments - [GitHub AI agent leaks private repositories via prompt injection attack](https://daily.dev/posts/github-ai-agent-leaks-private-repositories-via-prompt-injection-attack-ffq6gdzd6) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#cicd](https://daily.dev/tags/cicd), [#github-actions](https://daily.dev/tags/github-actions), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/wd82ycspd) ```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":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/wd82ycspd","headline":"My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli","text":"Shared: My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli","url":"https://daily.dev/posts/wd82ycspd","datePublished":"2026-05-30T11:17:29.901Z","dateModified":"2026-05-30T11:18:42.483Z","author":{"@type":"Person","name":"Nosa Shandy","url":"https://daily.dev/nosashandy","image":"https://avatars.githubusercontent.com/u/16370264?v=4","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":20}},"image":"https://media.daily.dev/image/upload/s--ZrL_HSsR--/f_auto/v1722860399/public/Placeholder%2006","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/SXupQut5A"},"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/securitythings","name":"Information Security Things"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Information Security Things","item":"https://daily.dev/squads/securitythings"},{"@type":"ListItem","position":3,"name":"My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli"}]} ```