The davila7 claude-code-templates CLI tool before version 1.29.4 contains an OS command injection vulnerability (CWE-78) due to improper neutralization of special elements in user-supplied input. The vulnerable server component binds to all network interfaces on port 3444 without authentication and permits cross-origin requests. The POST endpoints /api/execute and /api/install-agent accept attacker-controlled input fields that are passed directly to child_process.spawn() with shell execution enabled, allowing shell metacharacters to be interpreted. This enables remote attackers who can reach the port or induce developers to visit malicious sites to execute arbitrary OS commands with the privileges of the developer running the Studio server. The vulnerability is addressed in version 1.29.4.

Successful exploitation allows remote attackers to execute arbitrary operating system commands with the privileges of the developer running the Studio server. This can lead to compromise of source code, credentials, and local data. The vulnerability requires either direct network access to the exposed port 3444 or social engineering to convince a developer to visit a malicious website. The CVSS 3.1 base score is 8.8 (High), reflecting network attack vector, low attack complexity, no privileges required, user interaction required, and high impact on confidentiality, integrity, and availability.

This vulnerability is fixed in version 1.29.4 of claude-code-templates. Users should upgrade to version 1.29.4 or later to remediate this issue. Until upgraded, restrict network access to port 3444 to trusted hosts only and avoid running the Studio server in untrusted environments. There is no official patch or temporary fix other than upgrading. No vendor advisory content is provided to indicate alternative mitigations or that no action is required.