Platform
Solutions
Resources
Company
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 ResearchAI & Agent Security
Mitiga Labs Team
Read the Post →Identity & Access
Threat Hunting & Detection
Ucha Gobejishvili
Read the Post →AWS
Threat Hunting & Detection
Yafit Shayo
Read the Post →
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 WorksLet them come
A Research Report from Mitiga Labs
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.
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.
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
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 →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 →Identity & Access
Threat Hunting & Detection
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 →AWS
Threat Hunting & Detection
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 →Threat Hunting & Detection
AI Agents & MCP
How Mitiga built automated detection engineering, or FORGE, a multi-agent harness that drafts, adversarially validates, and reachability-tests detection rules against real customer data, with humans still in the loop.
Roei Sherman
Read the Post →AI Agents & MCP
Identity & Access
A fake take-home coding test hid instructions that made a developer’s own AI assistant steal cloud credentials in under two minutes — no malware. The full attack chain and how to contain it.
Ucha Gobejishvili
Read the Post →AI Agents & MCP
Attack Research
Mitiga Labs scanned 50,000+ AI instruction files across 7,000+ repos and found hijacked Claude base URLs and 1,230+ leaking API keys — plus a free scanner, Skillgate.
Idan Cohen
Read the Post →AI Agents & MCP
What's the difference between MCP and an API? One's built for code, the other for AI agents. Here's when to use each and why you need both.
Roi Tirosh
Read the Post →Threat Hunting & Detection
Cloud Forensics & Logging
Mitiga Labs shows how cloud threat hunting connects identity, control-plane, and data-plane evidence into attack chains defenders can investigate and contain.
Ucha Gobejishvili
Read the Post →AI Agents & MCP
Identity & Access
Mitiga Labs shows how attackers steal MCP tokens from Claude Code to bypass SSO, MFA, and authentication. Learn top detection strategies for AI coding security.
Idan Cohen
Read the Post →SaaS Applications
Breach & Campaign Analysis
Stop the next supply chain attack. See how ShinyHunters compromised Rockstar via a Snowflake data breach. Get the tactical threat hunting tips your SOC needs.
Idan Cohen
Read the Post →Head of Cloud Security Research
Senior Incident Responder
Senior Director, Mitiga Research
Cloud Researcher
Cloud Security Researcher
Cloud Security Researcher
Cloud Security Researcher
Cloud Security Researcher
AI Detection and Response for modern infrastructure. Defend with AI, from AI, and your AI.
Learn more
