DeepSeek-Reasonix: How a poisoned config can hijack an AI coding agent
GitLab's Threat Research Group found a flaw, ConfigPoisoning, that runs attacker code when a developer views a file's diff in DeepSeek-Reasonix.
Read PostBrowse articles that include the security research tag
Featured post
Recent posts
Security Labs
Critical remote code execution in Serena, a popular MCP coding agent
GitLab's Threat Research Group found a critical template injection in Serena that runs attacker code the moment a developer opens a repository.
Security Labs
A sandbox is only as closed as what an AI agent can reach
Stuck in an evaluation with no way out, an AI agent escaped in an hour through the one service on its allowlist. Here's the gap that opened.
Security
How GitLab tracks vulnerabilities through refactors and reformatting
Learn how GitLab's improved Scope+Offset fingerprinting keeps vulnerability tracking stable across comments, blank lines, and reformatting.
Security Labs
How to detect and prevent Contagious Interview IDE attacks
Learn how we built custom controls that detect and prevent malware campaigns like those used for Contagious Interview and how to deploy them in your environment.
Security Labs
Build an automated detection testing framework with GitLab CI/CD and Duo
Learn how GitLab's Signals Engineering team built the WATCH framework to continuously validate our security monitoring pipeline.
Security Labs
Automating detection gap analysis with GitLab Duo Agent Platform
Learn how GitLab's Signals Engineering team uses our AI platform to automatically surface detection gaps from security incidents — no manual review required.
Security Labs
GitLab Threat Intelligence Team reveals North Korean tradecraft
Gain threat intelligence about North Korea’s Contagious Interview and fake IT worker campaigns and learn how GitLab disrupted their operations.
Find out which plan works best for your team
Learn about pricingLearn about what GitLab can do for your team
Talk to an expert