MITIGA LABS
Welcome to Mitiga Labs, our research and innovation arm built to expose how modern attackers operate in Cloud and SaaS. We break down real campaigns and publish practical guidance tohelp security teams stop cloud attacks from having impact. Our research powers the Zero-Impact Breach Prevention approach at the core of the Mitiga platform.
The Cloud Attack Campaigns and Research that Defined a Year.
2025 was the year the threat got smarter. Attackers skipped zero-days and walked in through trusted identities, OAuth links, API chains, and lateral SaaS paths.
LET THEM COME
A Threat Intelligence Report from Mitiga Labs
Mitiga Labs is where we tear into the latest Cloud, SaaS, AI, and Identity attacks. Our researchers decode how adversaries operate and turn that knowledge into defense strategies that stop cloud attacks from having impact. Every discovery fuels Mitiga’s Zero-Impact Breach Prevention.
Explore the latest discoveries, deep dives, and technical how-tos from the Mitiga Labs team. Our research is dedicated to informing defenders and disrupting attackers.
What Supply Chain Attacks Teach Incident Responders
Supply chain attacks hide behind trusted vendors. Learn how incident responders detect, scope, and contain vendor compromise in cloud and SaaS environments.
Read MoreRESEARCHERS
Jed MorleyAI Agent Supply Chain Risk: Silent Codebase Exfiltration via Skills
Mitiga Labs shows how a malicious AI agent skill can silently exfiltrate an entire codebase, exposing a new supply chain risk in agentic AI environments.
Read MoreRESEARCHERS
Idan CohenBrainjacked: Planting a False Reality in the AI Training Pipeline
A real-world AI supply chain attack shows how path traversal enabled training data poisoning, embedding a persistent backdoor in a production ML model.
Read MoreRESEARCHERS
Ucha GobejishviliConsentFix OAuth Phishing Explained: How Token-Based Attacks Bypass MFA in Microsoft Entra ID
ConsentFix is a new OAuth phishing technique abusing Microsoft Entra ID to steal tokens without MFA. Learn how it works and how to protect against it.
Read MoreRESEARCHERS
Ucha GobejishviliInside the AI Supply Chain: Security Lessons from 10,000 Open-Source ML Projects
Analysis of 10,000 open-source AI/ML repositories reveals 70% have critical or high-severity vulnerabilities in GitHub Actions workflows, making them prone to attacks like code injection, credential theft, or repo takeover via malicious PRs.
Read MoreRESEARCHERS
Ucha GobejishviliHead of Cloud Security Research
Senior Incident Responder
Senior Director | Mitiga Research
Cloud Researcher
Senior Incident Responder
Cloud Security Researcher
Cloud Security Researcher
The next critical capability for Mitiga's Al-native CDR platform is here.
Explore our solution that empowers and automates SecOps, protects AI infrastructure, and defends against AI-sclaed attacks.
