[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fsvpWGRRulmKY8ygtJ_z6OWaN_mRUA8AbAJNbKqP50XI":3},{"article":4,"iocs":38,"watch_terms":39},{"id":5,"title":6,"slug":7,"summary":8,"ai_summary":9,"brief":10,"full_text":11,"url":12,"image_url":13,"published_at":14,"ingested_at":15,"relevance_score":16,"entities":17,"category_id":18,"category":19,"article_tags":22},"af27a9cc-f2ee-41f3-8962-43c8c0a90335","Google's Vertex AI Has an Over-Privileged Problem","google-s-vertex-ai-has-an-over-privileged-problem","Palo Alto researchers show how attackers could exploit AI agents on Google's Vertex AI to steal data and break into restricted cloud infrastructure.","Palo Alto Networks researchers discovered that Google's Vertex AI agents can be exploited due to excessive permissions, potentially allowing attackers to steal data and gain unauthorized access to restricted cloud infrastructure. The vulnerability stems from default configurations that grant AI agents more privileges than necessary. This highlights a critical gap in least-privilege implementation for AI workloads in cloud environments.","Palo Alto researchers reveal over-privileged Vertex AI agents could enable data theft and cloud infrastructure",null,"https:\u002F\u002Fwww.darkreading.com\u002Fcyber-risk\u002Fgoogles-vertex-ai-over-privilege-problem","https:\u002F\u002Feu-images.contentstack.com\u002Fv3\u002Fassets\u002Fblt6d90778a997de1cd\u002Fblt4e41a8645f65857e\u002F69cc23a696a9929cb14154a7\u002Fagent_Krot_Studio_shutterstock.jpg?width=1280&auto=webp&quality=80&disable=upscale","2026-03-31T20:26:33+00:00","2026-03-31T22:00:21.138073+00:00",8,[],"c70f3a41-2f0c-4608-870d-b8cbcd8be076",{"id":18,"icon":11,"name":20,"slug":21},"Cloud Security","cloud-security",[23,28,33],{"category":24},{"id":25,"icon":11,"name":26,"slug":27},"80544778-fabb-4dcd-aa35-17492e5dcf4f","Vulnerabilities","vulnerabilities",{"category":29},{"id":30,"icon":11,"name":31,"slug":32},"839da5c1-3c34-47e2-9499-f7201640e3ac","AI Security","ai-security",{"category":34},{"id":35,"icon":11,"name":36,"slug":37},"e7b231c8-5f79-4465-8d38-1ef13aea5a14","Threat Intelligence","threat-intelligence",[],[]]