davila7 claude-code-templates up to 1.29.3 Studio sandbox-server.js child_process.spawn prompt/agentName os command injection

Summaryinfo

A vulnerability identified as critical has been detected in davila7 claude-code-templates up to 1.29.3. This issue affects the function child_process.spawn of the file cli-tool/src/sandbox-server.js of the component Studio. Performing a manipulation of the argument prompt/agentName results in os command injection. This vulnerability is known as CVE-2026-73222. Remote exploitation of the attack is possible. No exploit is available.

Detailsinfo

A vulnerability, which was classified as critical, was found in davila7 claude-code-templates up to 1.29.3. This affects the function child_process.spawn of the file cli-tool/src/sandbox-server.js of the component Studio. The manipulation of the argument prompt/agentName with an unknown input leads to a os command injection vulnerability. CWE is classifying the issue as CWE-78. The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

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.

The advisory is shared at github.com. This vulnerability is uniquely identified as CVE-2026-73222 since 08/11/2026. The exploitability is told to be easy. It is possible to initiate the attack remotely. No form of authentication is needed for exploitation. Technical details are known, but no exploit is available. MITRE ATT&CK project uses the attack technique T1202 for this issue.

Upgrading to version 1.29.4 eliminates this vulnerability.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• davila7

Name

• claude-code-templates

Version

• 1.29.0
• 1.29.1
• 1.29.2
• 1.29.3

Website

• Product: https://github.com/davila7/claude-code-templates/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion