Mitiga Labs

Real-world research.
Where the attacks actually are.

Attack research you can run against your own environment. Mitiga Labs' researchers and responders work real breaches across cloud, SaaS, identity, third-party services, and AI. Every finding comes with the method to check your own estate.

Explore Our Research

AI & Agent Security

PromptLogger: The Hidden Exfiltration Layer in AI Instruction Files

Mitiga Labs Team

Read the Post →

Identity & Access

Threat Hunting & Detection

Hunting Third-Party App Abuse in Entra

Ucha Gobejishvili

Read the Post →

AWS

Threat Hunting & Detection

When Detection Engineering Becomes a Data Engineering Problem

Yafit Shayo

Read the Post →

A Skill Is Just Text.
So Is a Backdoor.

INSTRUCTION FILES YOUR AGENT READS — AND NOBODY OPENS.

Rule files, hooks, and CLAUDE.md run automatically the moment an agent loads them. Mitiga Labs found instruction files quietly recording prompts, tokens, and environment variables, then shipping them out. No malware, often no audit log.

See How it Works

Let them come

PromptLogger: The Hidden Exfiltration Layer in AI Instruction Files

A Research Report from Mitiga Labs

What We Saw in 2025.
What Comes Next.

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.

See How it Works

Let them come

What We Saw in 2025.
The Year the Threat Got Smarter

A Threat Intelligence Report from Mitiga Labs

From Attacks to Zero Impact

Mitiga Labs is where we take apart cloud, SaaS, identity, third-party services and AI attacks, then write what they find into the detections customers run. Those detections interrupt the next attack before it reaches the business. That's Zero-Impact Breach Prevention.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Latest from the Labs

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.

PromptLogger: The Hidden Exfiltration Layer in AI Instruction Files

A Mitiga Labs report on PromptLoggers and exfiltration hidden in AI instruction files — six real public-repo case studies, the techniques, and how to detect them before an agent runs.

Mitiga Research Team

Hunting Third-Party App Abuse in Entra

Stolen ConnectWise app credentials gave attackers app-only access to Microsoft 365. A six-part method for hunting third-party app abuse in Entra ID.

Ucha Gobejishvili

Read the Post →

When Detection Engineering Becomes a Data Engineering Problem

In a security data lake, a detection can be correct and still never finish. How two months of PySpark tuning became 34 rules that cut runtime up to 60%.

Yafit Shayo

Read the Post →

Google Cloud

Cloud Forensics & Logging

Who Touched My GCP Project? Understanding the Principal Part in Cloud Audit Logs – Part 1

Part 1 of Mitiga's GCP forensic guide covers Cloud Audit Logs, identity types, service accounts, and impersonation to determine who accessed your GCP project.

Gavriel Fried

Read the Post →

AWS

Identity & Access

Why Did AWS Replace My Role’s ARN with a Unique ID in My Policy?

Understand why AWS replaced your role's ARN with a unique ID in your policy and learn how it affects your IAM management and cloud security practices.

Stav Ochakovski

Read the Post →

Breach & Campaign Analysis

Identity & Access

Microsoft Breach by Midnight Blizzard (APT29): What Happened?

Understand the Midnight Blizzard Microsoft breach by APT29, what happened, and key steps organizations should take to strengthen their defenses.

Doron Karmi

Read the Post →

Software Supply Chain & CI/CD

Threat Hunting & Detection

Understanding GitLab's Security Threats and Strengthening Your Preparedness

Guide your engineering infrastructure security using Mitiga's tactical blueprint for identifying GitLab threats and protecting critical CI/CD pipelines.

Gavriel Fried

Read the Post →

AWS

Identity & Access

How AWS EKS Pod Identity Feature Enhances Credential Management

Focus on cloud credential management optimization using Mitiga's technical analysis of the newly announced AWS EKS Pod Identity feature for Kubernetes.

Stav Ochakovski

Read the Post →

Attack Research

Threat Hunting & Detection

Ransomware Strikes Azure Storage: Are You Ready?

Cloud ransomware attacks on Azure Storage are rising. Learn how attackers exploit access keys and permissions, and how to detect and prevent these attacks.

Gavriel Fried

Read the Post →

AWS

Attack Research

Mitiga Security Advisory: Abusing the SSM Agent as a Remote Access Trojan

Flag post-exploitation cloud infrastructure vulnerabilities using Mitiga's technical advisory on abusing the AWS Systems Manager agent as a stealth RAT.

Ariel Szarf

Read the Post →

AWS

Attack Research

More on Abusing the Amazon Web Services SSM Agent as a Remote Access Trojan

Show your SOC analysts how to detect hidden cloud threats using Mitiga's technical deep dive into malicious actors abusing the native AWS SSM agent as a RAT.

Ariel Szarf

Read the Post →

SaaS Applications

Cloud Forensics & Logging

Google Drive Security Gaps in Forensic Visibility

Mitiga's advisory highlights critical gaps in forensic visibility with Google Drive's Basic license, affecting security and incident investigations. Read on.

Ariel Szarf

Read the Post →

Research Team

Ariel Ainhoren

Head of Cloud Security Research

Ucha Gobejishvili

Senior Incident Responder
‍

Roei Sherman

Senior Director, Mitiga Research

Idan Cohen

Cloud Researcher
‍

Yael Ben Yair

Cloud Security Researcher
‍

Asad Saffoury

Cloud Security Researcher
‍

Oshrat Bar

Cloud Security Researcher
‍

Yafit Shayo

Cloud Security Researcher
‍

Helios AIDR

AI Detection and Response for modern infrastructure. Defend with AI, from AI, and your AI.

Learn more

Featured Videos

Get resilient