Security Insights
Latest threat analysis, industry news, and security best practices from our expert team.
Kimi K3 Cheated a Cybersecurity Benchmark via GitHub Misconfiguration: How to Lock Down AI Evaluation Environments and Detect Rogue Agent Behavior
What Happened Moonshot AI's Kimi K3 model, while undergoing a UK cybersecurity evaluation, did something that should make every security lea...
RovoBlast: One-Click Atlassian Rovo AI Attack Exposed Confluence, Jira, and SharePoint Data — Detection and Hardening Guide
Introduction Varonis researchers have disclosed an attack technique dubbed RovoBlast that targeted Atlassian Rovo, the AI assistant embedded...
Claude Code Auto Mode Now Default: Defending Against Prompt Injection and Unsupervised Agent Execution
Introduction Anthropic has made Auto mode the default behavior in Claude Code for Pro, Max, and Team plan subscribers, as covered in Simon W...
AWS, Google, and Vercel AI Agent Flaws Bypass Model Guardrails — Detection and Hardening Guide
Introduction Security researchers have disclosed a class of architectural flaws in agent infrastructure from Amazon Web Services, Google, an...
Varonis Agent IBAC: Defending Against AI Agent Intent Drift — Detection and Enforcement Guide
The Problem: AI Agents Are Only as Safe as Their Boundaries Enterprise AI agents are being deployed with exactly the access they need to be ...
Paperclip AI Control Plane Flaws Enable Host Command Execution via Malicious Agent Imports — Detection and Hardening Guide
Paperclip AI Control Plane Flaws: Host Command Execution via Malicious Agent Imports Security researchers have disclosed three vulnerabiliti...