Google's Gemini large language model (LLM) is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks.
The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Google Workspace as well as companies using the LLM API.
The first vulnerability involves
Cybersecurity researchers have detailed a "severe design flaw" in Google Workspace's domain-wide delegation (DWD) feature that could be exploited by threat actors to facilitate privilege escalation and obtain unauthorized access to Workspace APIs without super admin privileges.
"Such exploitation could result in theft of emails from Gmail, data exfiltration from Google Drive, or other
A set of novel attack methods has been demonstrated against Google Workspace and the Google Cloud Platform that could be potentially leveraged by threat actors to conduct ransomware, data exfiltration, and password recovery attacks.
"Starting from a single compromised machine, threat actors could progress in several ways: they could move to other cloned machines with GCPW installed, gain access
Any app that can improve business operations is quickly added to the SaaS stack. However, employees don't realize that this SaaS-to-SaaS connectivity, which typically takes place outside the view of the security team, significantly increases risk.
Whether employees connect through Microsoft 365, Google Workspace, Slack, Salesforce, or any other app, security teams have no way to quantify their
Login
FreshRSS