GitLab Duo Claude AI Agent Flaw Lets Attackers Execute Arbitrary Commands in CI Pipelines
27 de Agosto de 2026, 06:24
GitLab has released security updates for both its Community Edition and Enterprise Edition, addressing seven vulnerabilities, including a high-severity flaw in its Duo Claude AI agent. This vulnerability could allow authenticated developers to execute arbitrary commands within a CI (Continuous Integration) context. GitLab Duo Claude AI Agent Flaw The issue, tracked as CVE-2026-18252, arises from […]
The post GitLab Duo Claude AI Agent Flaw Lets Attackers Execute Arbitrary Commands in CI Pipelines appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform.

