NomaLabs

Noma Labs is an elite team of AI security researchers dedicated to uncovering enterprise AI vulnerabilities before attackers do. We’re using deep AI vulnerability research to provide organizations the knowledge and tools they need to enable AI innovation securely.

RufRoot: The MCP Bridge Vulnerability That Turns Agents Into Rogue Admins (CVE-2026-59726)

RufRoot: The MCP Bridge Vulnerability That Turns Agents Into Rogue Admins (CVE-2026-59726)

Eli Ainhorn

July 29, 2026

GitLost: How We Tricked GitHub’s AI Agent into Leaking Private Repos

GitLost: How We Tricked GitHub’s AI Agent into Leaking Private Repos

Sasi Levi

July 6, 2026

GrafanaGhost: The Phantom Stealing Your Data

GrafanaGhost: The Phantom Stealing Your Data

Sasi Levi

April 7, 2026

ContextCrush: The Context7 MCP Server Vulnerability Hiding in Plain Sight

ContextCrush: The Context7 MCP Server Vulnerability Hiding in Plain Sight

Eli Ainhorn

March 5, 2026

Hacking Google Gemini Enterprise with an Indirect Prompt Injection

Hacking Google Gemini Enterprise with an Indirect Prompt Injection

Gal Moyal

December 8, 2025

AI Agent risk exposed in Salesforce Agentforce

AI Agent risk exposed in Salesforce Agentforce

Gal Moyal

September 25, 2025

Enterprise Trust

Already trusted by leading Fortune 500 enterprises to protect their most critical AI systems in production.

explore platform

General Security Research

Read all about the latest from Noma.

The Great (Sandbox) Escape - Analyzing the OpenAI and Hugging Face Security Incident

The Great (Sandbox) Escape - Analyzing the OpenAI and Hugging Face Security Incident

August 12, 2026

Off the Map: When Autonomous Agents Go Rogue

Off the Map: When Autonomous Agents Go Rogue

Pandora’s Claw: From Internal Leak to Industry Standard

Pandora’s Claw: From Internal Leak to Industry Standard