Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution

The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system. The post Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution appeared first on SecurityWeek .

According to public reporting, the DuneSlide vulnerabilities (CVE-2026-50548 and CVE-2026-50549) in the Cursor AI code editor allow a single zero‑click prompt injection to escape the editor’s sandbox and execute arbitrary commands with OS‑level privileges on a developer’s machine, affecting all versions prior to Cursor 3.0.[6] These flaws demonstrate that seemingly benign prompts, especially when combined with AI‑augmented workflows and MCP/CLI integrations, can become a primary vector for remote code execution and full compromise of a developer environment.[2][6] From a CyberSE.AI perspective, this is a high‑severity prompt injection risk in an AI IDE that directly interacts with local files, shell commands, and external tools. Organizations should harden agent capabilities and sandbox boundaries, continuously red‑team AI workflows (including IDE agents and MCP servers), and treat AI toolchains as part of the software supply chain that require SBOM‑level visibility and patch management to prevent similar OS‑level compromises.