Google reportedly patched a flaw in the Vertex AI SDK for Python that could allow attackers to hijack model uploads and ...
Security researchers have identified a vulnerability in Google’s Vertex AI agent framework that could allow attackers to extract sensitive cloud data and proprietary code through indirect prompt ...
Google fixed a Vertex AI SDK flaw in v1.148.0 after Unit 42 showed bucket squatting could enable model hijacking and code ...
Unit 42 reveals misconfigured Vertex AI agents in Google Cloud can be hijacked into “double agents” Excessive default permissions let attackers pivot, access Cloud Storage, and expose proprietary ...