[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fv4l4F0bty04c5G2LY8xbvdkH0f5dt_V1H4oA69lXMbA":3},{"article":4,"iocs":54,"iocs_total":55,"watch_terms":56,"solutions":57,"lesson":148},{"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":31,"category":32,"article_tags":36},"40ef1f8c-3385-40d8-be63-7e103a5061ef","Google puts new limits on AI agents that hunt threats and fix vulnerabilities","google-puts-new-limits-on-ai-agents-that-hunt-threats-and-fix-vulnerabilities-b3f899","Google Cloud is adding new controls to CodeMender, its AI tool for finding and fixing software vulnerabilities, allowing businesses to isolate attack simulations and target code scans more precisely. The updates let businesses verify vulnerabilities and simulate exploits in an operating system-level sandbox or an isolated virtual machine. They also add human checks for local writes and command execution to help keep testing within defined limits. Businesses can scan an entire code repository, a specific … More → The post Google puts new limits on AI agents that hunt threats and fix vulnerabilities appeared first on Help Net Security.","Google Cloud is introducing new controls for its AI tool, CodeMender, to enhance security in threat detection and vulnerability fixing. These updates allow businesses to isolate attack simulations and conduct more precise code scans within sandboxed environments, incorporating human checks to maintain oversight. The enhancements also extend to AI agent security across various Google Cloud services, aiming to manage credentials, protect data, and detect threats more effectively in multicloud environments.","Google Cloud enhances CodeMender AI with new controls for threat simulation and vulnerability scanning.","https:\u002F\u002Fwww.helpnetsecurity.com\u002F2026\u002F11\u002F05\u002Fgoogle-cloud-ai-agents-security-controls\u002F","https:\u002F\u002Fimg.helpnetsecurity.com\u002Fwp-content\u002Fuploads\u002F2026\u002F05\u002F10114938\u002Fgoogle-ai-robot.webp","2026-11-05T11:02:43+00:00","2026-11-05T12:00:14.584264+00:00",7,[17,20,23,25,27,29],{"name":18,"type":19},"CodeMender","product",{"name":21,"type":22},"Google","vendor",{"name":24,"type":19},"Gemini",{"name":26,"type":19},"Google Kubernetes Engine",{"name":28,"type":19},"Cloud Run",{"name":30,"type":19},"Agent Compute Engine","839da5c1-3c34-47e2-9499-f7201640e3ac",{"id":31,"icon":33,"name":34,"slug":35},null,"AI Security","ai-security",[37,42,44,49],{"category":38},{"id":39,"icon":33,"name":40,"slug":41},"02371804-cf6d-4449-98de-f1a2d4d9b266","Tools","tools",{"category":43},{"id":31,"icon":33,"name":34,"slug":35},{"category":45},{"id":46,"icon":33,"name":47,"slug":48},"c70f3a41-2f0c-4608-870d-b8cbcd8be076","Cloud Security","cloud-security",{"category":50},{"id":51,"icon":33,"name":52,"slug":53},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[],0,[21,18,24],{"controls":58,"vendors":142},[59,88,117],{"slug":60,"name":61,"problem":62,"products":63},"identity-threat-detection","Identity threat detection and response (ITDR)","Attackers who log in with real, stolen credentials get noticed.",[64,72,80],{"vendor_slug":65,"vendor_name":66,"vendor_logo":67,"product_slug":68,"product_name":69,"url":70,"description":71},"microsoft","Microsoft","\u002Fvendor-logos\u002Fmicrosoft.png","defender-for-identity","Microsoft Defender for Identity","https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fsecurity\u002Fbusiness\u002Fsiem-and-xdr\u002Fmicrosoft-defender-for-identity","Detects attacks against on-premises Active Directory and hybrid identities.",{"vendor_slug":73,"vendor_name":74,"vendor_logo":75,"product_slug":76,"product_name":77,"url":78,"description":79},"okta","Okta","\u002Fvendor-logos\u002Fokta.png","identity-threat-protection","Okta Identity Threat Protection","https:\u002F\u002Fwww.okta.com\u002Fproducts\u002Fidentity-threat-protection\u002F","Continuous risk assessment of sessions after login, with automatic actions such as ending sessions.",{"vendor_slug":81,"vendor_name":82,"vendor_logo":83,"product_slug":84,"product_name":85,"url":86,"description":87},"vectra-ai","Vectra AI","\u002Fvendor-logos\u002Fvectra-ai.png","vectra-ai-platform","Vectra AI Platform","https:\u002F\u002Fwww.vectra.ai\u002Fplatform","Detection of attacker behaviour across network, identity and cloud.",{"slug":89,"name":90,"problem":91,"products":92},"secrets-management","Secrets management","API keys, tokens and passwords stop leaking from code, chat and configuration files.",[93,101,109],{"vendor_slug":94,"vendor_name":95,"vendor_logo":96,"product_slug":97,"product_name":98,"url":99,"description":100},"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":102,"vendor_name":103,"vendor_logo":104,"product_slug":105,"product_name":106,"url":107,"description":108},"palo-alto-networks","Palo Alto Networks","\u002Fvendor-logos\u002Fpalo-alto-networks.png","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.",{"vendor_slug":110,"vendor_name":111,"vendor_logo":112,"product_slug":113,"product_name":114,"url":115,"description":116},"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.",{"slug":35,"name":118,"problem":119,"products":120},"AI application security","Prompt injection, data leaks through AI tools and unapproved AI use get caught.",[121,129,134],{"vendor_slug":122,"vendor_name":123,"vendor_logo":124,"product_slug":125,"product_name":126,"url":127,"description":128},"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":122,"vendor_name":123,"vendor_logo":124,"product_slug":130,"product_name":131,"url":132,"description":133},"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.",{"vendor_slug":135,"vendor_name":136,"vendor_logo":137,"product_slug":138,"product_name":139,"url":140,"description":141},"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.",[143],{"slug":144,"name":21,"logo_path":145,"roles":146},"google","\u002Fvendor-logos\u002Fgoogle.png",[147],"reported_by",{"slug":149,"title":150,"body":151,"framework_refs":152,"framework_notes":159},"google-adds-human-oversight-and-sandboxing-controls-to-ai-security-agents","Google Adds Human Oversight and Sandboxing Controls to AI Security Agents","As AI agents take on increasingly autonomous roles in threat hunting and vulnerability remediation, the absence of proper guardrails introduces significant risks — including unintended code changes, credential misuse, and unchecked attack simulations running in production environments. Google's CodeMender updates highlight that AI-driven security tools must themselves be secured with the same rigor applied to any privileged system. Without sandboxing, human checkpoints, and strict credential management, an AI agent could become a high-privilege attack surface or cause operational disruption. This matters because autonomous AI tools operate at speed and scale that humans cannot easily supervise, amplifying the impact of any misconfiguration or compromise.",[153,154,155,156,157,158,156],"CIS Control 5: Account Management","CIS Control 12: Network Infrastructure Management","NIST SP 800-53 SI-2: Flaw Remediation","NIST CSF 2.0 PR.AA: Identity Management, Authentication, and Access Control","ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities","DORA Article 9",{"DORA Article 9":160,"CIS Control 5: Account Management":161,"NIST SP 800-53 SI-2: Flaw Remediation":162,"CIS Control 12: Network Infrastructure Management":163,"ISO\u002FIEC 27001:2022 A.8.8: Management of technical vulnerabilities":164,"NIST CSF 2.0 PR.AA: Identity Management, Authentication, and Access Control":165},"Financial entities deploying AI agents for security operations must ensure those agents meet ICT security requirements, including controls on automated actions that could affect operational continuity.","AI agents require privileged credentials; enforcing least-privilege and regular review of agent identities directly addresses the credential misuse risk highlighted in this article.","AI-assisted vulnerability fixing must still follow a controlled remediation workflow with human validation to ensure fixes are accurate and do not introduce new flaws.","Sandboxing AI-driven attack simulations requires deliberate network segmentation to ensure test activity cannot reach production systems.","Automated vulnerability scanning and remediation by AI agents must operate within a structured vulnerability management process that includes human oversight and change control.","Restricting what AI agents can access and do in a multicloud environment maps directly to the access control protections required to prevent privilege escalation or data exposure."]