MEDIUMMalware
Global

Double Agents: Exposing Security Blind Spots in GCP Vertex AI

Tuesday, March 31, 2026 at 10:00 AM UTC·Source: Unit 42 (Palo Alto)

Updated: Thursday, April 2, 2026 at 05:46 PM UTC

Executive Summary

Unit 42 uncovers a "double agent" flaw in Google Cloud's Vertex AI, demonstrating how overprivileged AI agents can compromise cloud environments. The post Double Agents: Exposing Security Blind Spots in GCP Vertex AI appeared first on Unit 42 .

Analysis

Unit 42 uncovers a "double agent" flaw in Google Cloud's Vertex AI, demonstrating how overprivileged AI agents can compromise cloud environments. The post Double Agents: Exposing Security Blind Spots in GCP Vertex AI appeared first on Unit 42 .
Source Attribution

Originally published by Unit 42 (Palo Alto) on Mar 31, 2026.

Related Threats

MEDIUMMalware

Claude Code leak used to push infostealer malware on GitHub

Threat actors are exploiting the recent Claude Code source code leak by using fake GitHub repositories to deliver Vidar information-stealing malware. [...]

BleepingComputer
MEDIUMMalware

Bank Trojan 'Casbaneiro' Worms Through Latin America

Augmented Marauder's multipronged banking-Trojan cyber campaigns are targeting Spanish speakers, evading detection, and replicating rapidly.

Dark Reading
MEDIUMMalware

GitHub Used as Covert Channel in Multi-Stage Malware Campaign

LNK files use GitHub C2, embedded decoders and PowerShell for persistence and data exfiltration

Infosecurity Magazine