Claude Code Templates is a CLI tool for configuring and monitoring Claude Code. Prior to 1.29.4, the Claude Code Studio server launched by the --studio option in cli-tool/src/sandbox-server.js binds to all interfaces on port 3444, permits cross-origin requests, and requires no authentication. The POST /api/execute endpoint passes the prompt request-body field to executeLocalTask(), and POST /api/install-agent passes the agentName request-body field to a child process. The same unsafe agent field path is reachable from /api/execute through checkAndInstallAgent(). These attacker-controlled values reach child_process.spawn() with shell execution enabled, causing Node.js to construct a shell command in which metacharacters are interpreted. An attacker who can reach the port directly, or who convinces a developer running Studio to visit a malicious website, can execute arbitrary operating-system commands with the developer's privileges and compromise source code, credentials, and local data. This issue is fixed in version 1.29.4.
Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Thu, 13 Aug 2026 15:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Thu, 13 Aug 2026 10:15:00 +0000

Type Values Removed Values Added
First Time appeared Davila7
Davila7 claude-code-templates
Vendors & Products Davila7
Davila7 claude-code-templates

Tue, 11 Aug 2026 18:45:00 +0000

Type Values Removed Values Added
Description Claude Code Templates is a CLI tool for configuring and monitoring Claude Code. Prior to 1.29.4, the Claude Code Studio server launched by the --studio option in cli-tool/src/sandbox-server.js binds to all interfaces on port 3444, permits cross-origin requests, and requires no authentication. The POST /api/execute endpoint passes the prompt request-body field to executeLocalTask(), and POST /api/install-agent passes the agentName request-body field to a child process. The same unsafe agent field path is reachable from /api/execute through checkAndInstallAgent(). These attacker-controlled values reach child_process.spawn() with shell execution enabled, causing Node.js to construct a shell command in which metacharacters are interpreted. An attacker who can reach the port directly, or who convinces a developer running Studio to visit a malicious website, can execute arbitrary operating-system commands with the developer's privileges and compromise source code, credentials, and local data. This issue is fixed in version 1.29.4.
Title Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)
Weaknesses CWE-306
CWE-352
CWE-78
References
Metrics cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'}


Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-08-13T13:54:28.645Z

Reserved: 2026-08-11T14:41:20.122Z

Link: CVE-2026-73222

cve-icon Vulnrichment

Updated: 2026-08-13T13:53:53.739Z

cve-icon NVD

Status : Received

Published: 2026-08-11T19:18:51.720

Modified: 2026-08-13T15:20:08.913

Link: CVE-2026-73222

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-13T09:49:42Z

Weaknesses