GitLab Duo Vulnerability Enabled Attackers to Hijack AI Responses with Hidden Prompts
Cybersecurity researchers have discovered an indirect prompt injection flaw in GitLab’s artificial intelligence (AI) assistant Duo that could have allowed attackers to steal source code and inject untrusted HTML into…
Chinese gov’t hackers exploiting new Atlassian vulnerability, Microsoft says
Hackers linked to the Chinese government are exploiting a recently-discovered vulnerability affecting an Atlassian product, according to Microsoft. In a notice on Tuesday evening, Microsoft said it has seen a…