[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fYm9S_F6gVyk2SNmmv2kr17lqv8FnhqELDVMa705gCTM":3},{"article":4,"iocs":46,"watch_terms":47,"solutions":48,"lesson":136},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"url":11,"image_url":12,"published_at":13,"ingested_at":14,"relevance_score":15,"entities":16,"category_id":28,"category":29,"article_tags":33},"284cac6c-4860-48e6-88a3-a111995a3f63","Google Deletes 3 ADK AI Workflows After Malicious GitHub Issue Could Trigger Privileged Agent","google-deletes-3-adk-ai-workflows-after-malicious-github-issue-could-trigger-pri-06b31a","Google deleted three AI agent workflows from its Agent Development Kit (ADK) Python repository. Pillar Security showed that a public GitHub issue could manipulate a triage agent into triggering a privileged code-fixing agent. The researchers said the public agent could be prompt-injected into posting \u002Fadk-issue-fix as adk-bot. They identified the bot as a collaborator, so that comment satisfied","Google removed three AI agent workflows from its ADK Python repository after Pillar Security discovered a vulnerability. A public GitHub issue could be manipulated to trigger a privileged code-fixing agent, leading to arbitrary code execution on the CI runner and potential exfiltration of sensitive credentials like a bot PAT and Google API key. The exposed component was the repository automation, not the ADK package itself.","Google deletes AI workflows after GitHub issue could trigger privileged agent.","https:\u002F\u002Fthehackernews.com\u002F2026\u002F08\u002Fgoogle-deletes-3-adk-ai-workflows-after.html","https:\u002F\u002Fblogger.googleusercontent.com\u002Fimg\u002Fb\u002FR29vZ2xl\u002FAVvXsEhLUUlqxE9AYL9PyFAlWMsG9czDcrU9p2kMUsumVIYx5SnlMAO0z-n_weUWeX-CiMHQBbkGK1lV-78vp003-bAeRP4gQRyGXlq5blzx5dJdd9zFttd2tjhGlNUFLNk-6ro9GfXMkRCFVLs-ex3gWHoJh-87sZifOeTKohLNoypvvqLUUPLkGUsjKXfAj7A\u002Fs1600\u002Fgoogle.gif","2026-08-04T11:16:23+00:00","2026-08-04T14:00:26.498669+00:00",8,[17,20,23,26],{"name":18,"type":19},"Agent Development Kit (ADK)","product",{"name":21,"type":22},"Google","vendor",{"name":24,"type":25},"AI","technology",{"name":27,"type":25},"GitHub Actions","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":28,"icon":30,"name":31,"slug":32},null,"AI Security","ai-security",[34,39,41],{"category":35},{"id":36,"icon":30,"name":37,"slug":38},"80544778-fabb-4dcd-aa35-17492e5dcf4f","Vulnerabilities","vulnerabilities",{"category":40},{"id":28,"icon":30,"name":31,"slug":32},{"category":42},{"id":43,"icon":30,"name":44,"slug":45},"c70f3a41-2f0c-4608-870d-b8cbcd8be076","Cloud Security","cloud-security",[],[21,18],{"controls":49,"vendors":130},[50,79,105],{"slug":51,"name":52,"problem":53,"products":54},"privileged-access-management","Privileged access management (PAM)","Admin accounts stop being one stolen password away from control of everything.",[55,63,71],{"vendor_slug":56,"vendor_name":57,"vendor_logo":58,"product_slug":59,"product_name":60,"url":61,"description":62},"wallix","WALLIX","\u002Fvendor-logos\u002Fwallix.png","wallix-pam","WALLIX PAM","https:\u002F\u002Fwww.wallix.com\u002Fproducts\u002Fprivileged-access-management-software\u002F","Privileged access management with session recording, for IT and OT environments.",{"vendor_slug":64,"vendor_name":65,"vendor_logo":66,"product_slug":67,"product_name":68,"url":69,"description":70},"delinea","Delinea","\u002Fvendor-logos\u002Fdelinea.png","secret-server","Delinea Secret Server","https:\u002F\u002Fdelinea.com\u002Fproducts\u002Fsecret-server","Vault for privileged credentials with discovery, rotation and session recording.",{"vendor_slug":72,"vendor_name":73,"vendor_logo":74,"product_slug":75,"product_name":76,"url":77,"description":78},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","idira-privileged-access-management","Idira Privileged Access Management","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fidira\u002Fhuman\u002Fprivileged-access-management","Privileged access management from the former CyberArk portfolio: vaulting, rotation, just-in-time access and session monitoring.",{"slug":80,"name":81,"problem":82,"products":83},"secrets-management","Secrets management","API keys, tokens and passwords stop leaking from code, chat and configuration files.",[84,92,100],{"vendor_slug":85,"vendor_name":86,"vendor_logo":87,"product_slug":88,"product_name":89,"url":90,"description":91},"gitguardian","GitGuardian","\u002Fvendor-logos\u002Fgitguardian.png","gitguardian-platform","GitGuardian Secrets Detection","https:\u002F\u002Fwww.gitguardian.com\u002F","Finds and helps remediate secrets leaked in repositories, CI pipelines and chat tools.",{"vendor_slug":93,"vendor_name":94,"vendor_logo":95,"product_slug":96,"product_name":97,"url":98,"description":99},"github","GitHub","\u002Fvendor-logos\u002Fgithub.png","advanced-security","GitHub Advanced Security","https:\u002F\u002Fgithub.com\u002Fsecurity\u002Fadvanced-security","Dependency review, code scanning and secret scanning with push protection.",{"vendor_slug":72,"vendor_name":73,"vendor_logo":74,"product_slug":101,"product_name":102,"url":103,"description":104},"idira-secrets-management","Idira Secrets Management","https:\u002F\u002Fwww.paloaltonetworks.com\u002Fidira\u002Fmachine\u002Fsecrets-management","Secrets management for applications, scripts and pipelines, from the former CyberArk portfolio.",{"slug":32,"name":106,"problem":107,"products":108},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[109,117,125],{"vendor_slug":110,"vendor_name":111,"vendor_logo":112,"product_slug":113,"product_name":114,"url":115,"description":116},"boomi","Boomi","\u002Fvendor-logos\u002Fboomi.png","boomi-ai-gateway","Boomi AI Gateway","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fai-gateway\u002F","Gateway for AI model and MCP tool traffic, built on Lunar.dev technology. It limits which tools each agent can call. Its enterprise version adds an approval step for new MCP servers and logs each call with the user or agent behind it.",{"vendor_slug":118,"vendor_name":119,"vendor_logo":120,"product_slug":121,"product_name":122,"url":123,"description":124},"hiddenlayer","HiddenLayer","\u002Fvendor-logos\u002Fhiddenlayer.png","hiddenlayer-ai-security","HiddenLayer AI Security Platform","https:\u002F\u002Fhiddenlayer.com\u002F","Model scanning, AI red teaming and runtime protection for AI applications.",{"vendor_slug":110,"vendor_name":111,"vendor_logo":112,"product_slug":126,"product_name":127,"url":128,"description":129},"boomi-agentstudio","Boomi Agentstudio","https:\u002F\u002Fboomi.com\u002Fplatform\u002Fagentstudio\u002F","Agent builder whose Agent Control Tower registers and monitors Boomi agents and agents on Amazon Bedrock, Microsoft Copilot and other platforms, keeps audit logs and can switch agents off where the provider allows it.",[131],{"slug":132,"name":21,"logo_path":133,"roles":134},"google","\u002Fvendor-logos\u002Fgoogle.png",[135],"affected",{"slug":137,"title":138,"body":139,"framework_refs":140,"framework_notes":151},"malicious-github-issue-exploits-privileged-ai-agent-in-google-adk-repo","Malicious GitHub Issue Exploits Privileged AI Agent in Google ADK Repo","A publicly accessible GitHub issue was weaponized to trigger a privileged CI\u002FCD agent in Google's ADK Python repository, enabling arbitrary code execution on the CI runner. The root problem was that an automated code-fixing agent operated with excessive privileges and lacked proper input validation against untrusted public input. This exposed sensitive credentials — including a bot Personal Access Token (PAT) and Google API key — to potential exfiltration. The incident highlights the growing attack surface introduced by AI-powered automation workflows embedded in CI\u002FCD pipelines. Granting elevated permissions to agents that process untrusted, user-supplied content is a critical misconfiguration that can undermine an entire software supply chain.",[141,142,143,144,145,146,147,148,149,150],"CIS Control 4: Controlled Use of Administrative Privileges","CIS Control 6: Access Control Management","CIS Control 16: Application Software Security","NIST SP 800-53 AC-6: Least Privilege","NIST SP 800-53 IA-5: Authenticator Management","NIST SP 800-53 SA-15: Development Process, Standards, and Tools","NIST SP 800-204C: DevSecOps for Microservices-Based Applications","SLSA Supply Chain Levels for Software Artifacts (Level 3: Isolated Build Environments)","OWASP CI\u002FCD Security Top 10: CICD-SEC-4 Poisoned Pipeline Execution (PPE)","OWASP CI\u002FCD Security Top 10: CICD-SEC-6 Insufficient Credential Hygiene",{}]