Researchers managed to trick GitLab’s AI-powered coding assistant to display malicious content to users and leak private source code by injecting hidden prompts in code comments, commit messages and ...

A critical vulnerability in GitLab’s AI-powered coding assistant, Duo, has exposed private source code repositories to theft through a sophisticated indirect prompt injection attack, cybersecurity ...

Marketers promote AI-assisted developer tools as workhorses that are essential for today’s software engineer. Developer platform GitLab, for instance, claims its Duo chatbot can “instantly generate a ...

An indirect prompt injection flaw in GitLab's artificial intelligence (AI) assistant could have allowed attackers to steal source code, direct victims to malicious websites, and more. In fact, ...