{"id":"CVE-2026-73222","aliases":["EUVD-2026-56858","GHSA-79wm-x847-7cvg"],"status":"published","title":"Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)","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.","severity":{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00319,"percentile":0.2515,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-306","CWE-352","CWE-78"],"published":"2026-08-11T18:27:09Z","modified":"2026-10-28T02:31:14Z","fixes":[{"ecosystem":"npm","package":"claude-code-templates","fixed_in":["1.29.4"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"claude-code-templates","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"1.29.2"},{"fixed":"1.29.4"}]}]},{"source":"osv","ecosystem":"npm","package":"claude-code-templates","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"1.29.4"}]}]}],"products":[{"vendor":"davila7","product":"claude-code-templates"}],"references":[{"url":"https://github.com/davila7/claude-code-templates/security/advisories/GHSA-79wm-x847-7cvg","tags":["x_refsource_CONFIRM","exploit","advisory","web"]},{"url":"https://github.com/davila7/claude-code-templates/commit/bc4618b07232633c1c0aac12a43e436268d31783","tags":["x_refsource_MISC","fix","web"]},{"url":"https://github.com/davila7/claude-code-templates/blob/main/CHANGELOG.md","tags":["x_refsource_MISC","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-73222","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-79wm-x847-7cvg"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73222.json","tags":["advisory"]},{"url":"https://github.com/davila7/claude-code-templates","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-73222","title":"Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)","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.","status":"published","published":"2026-08-11T18:27:09.297Z","modified":"2026-08-13T13:54:28.645Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-78","CWE-306","CWE-352"],"updated_at":"2026-11-02T13:43:22.599321Z"}],"euvd":[{"id":"EUVD-2026-56858","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.","status":"published","published":"2026-08-11T18:27:09Z","modified":"2026-08-13T13:54:28Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"updated_at":"2026-11-02T18:01:56.761721Z"}],"ghsa":[{"id":"GHSA-79wm-x847-7cvg","title":"Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)","description":"### Summary\n`npx claude-code-templates --studio` launches \"Claude Code Studio\", an Express HTTP server (`cli-tool/src/sandbox-server.js`, default port 3444) that binds to **all interfaces** (`0.0.0.0`), sets `Access-Control-Allow-Origin: *`, and requires **no authentication**. Two POST endpoints pass attacker-controlled request-body fields into `child_process.spawn(..., { shell: true })`. Because `shell: true` makes Node join the argv array into a single `sh -c` string, the fields are parsed by the shell and metacharacters execute. Any unauthenticated attacker who can reach the port — a malicious web page the developer visits, or anyone on the same LAN — can execute arbitrary OS commands on the developer's machine.\n\n### Details\nIn `cli-tool/src/sandbox-server.js`:\n\n- `app.listen(PORT, ...)` is called with no host argument, so the server listens on `0.0.0.0` / `::` (reachable from the LAN, not just localhost).\n- The CORS middleware sends `Access-Control-Allow-Origin: *` and answers the preflight `OPTIONS` for any origin, so a browser will deliver cross-origin POSTs to it.\n- There is no authentication on any endpoint.\n\nThe vulnerable sinks:\n\n1. `POST /api/execute` — the `prompt` body field flows into `executeLocalTask()`:\n   ```js\n   const child = spawn('claude', [finalPrompt], { /* ... */ shell: true });\n   The only validation on prompt is a length check (\u003e= 10 chars). With shell: true, finalPrompt is interpreted by the shell.\n\n2. POST /api/install-agent — the agentName body field:\nconst child = spawn('npx', ['claude-code-templates@latest', '--agent', agentName, '--yes'], { /* ... */ shell: true });\n2. agentName is used unvalidated. (The same unsafe pattern is also reachable through /api/execute's agent field via checkAndInstallAgent().)\n\nRoot cause: spawn(cmd, argsArray, { shell: true }) does not keep argsArray as separate argv entries — Node builds cmd + ' ' + argsArray.join(' ') and runs it via sh -c, so every element is subject to shell parsing.\n\nPoC\n\n# Victim\nnpx claude-code-templates --studio          # server on 0.0.0.0:3444\n\n# Attacker (another LAN host, or a malicious web page fetch(), or locally)\ncurl -s -X POST http://127.0.0.1:3444/api/execute \\\n  -H 'Content-Type: application/json' \\\n  --data '{\"prompt\":\"aaaaaaaaaa; touch /tmp/CCT_RCE_PROOF\",\"mode\":\"local\"}'\n\ncurl -s -X POST http://127.0.0.1:3444/api/install-agent \\\n  -H 'Content-Type: application/json' \\\n  --data '{\"agentName\":\"x; touch /tmp/CCT_AGENT_PROOF #\"}'\n\nls -la /tmp/CCT_RCE_PROOF /tmp/CCT_AGENT_PROOF   # both created =\u003e injected commands ran\nThe aaaaaaaaaa padding satisfies the 10-char minimum, then ; (or $(...), or backticks) starts the injected command. claude/npx do not even need to be installed — the injected segment runs regardless.\n\nConfirmed at runtime on v1.28.13 (Node 22, Linux): both marker files were created, the server listened on *:3444, and an OPTIONS preflight from Origin: https://evil.example returned 200 with Access-Control-Allow-Origin: *.\n\nImpact\n\nUnauthenticated remote code execution (CWE-78) on any machine running --studio. Two reachability paths:\n- Drive-by: a developer running --studio who visits an attacker-controlled web page — the page's cross-origin fetch() (Content-Type application/json) passes the wildcard CORS preflight and delivers the POST, achieving RCE with no other interaction.\n- LAN: because the server binds 0.0.0.0, anyone on the same network (office, co-working space, public Wi-Fi) can hit port 3444 directly.\n\nImpact is full compromise of the developer's user account (arbitrary command execution with the developer's privileges): source code, SSH keys, cloud credentials, and .env secrets.\n\nSuggested fix\n\n- Remove shell: true from all three spawns so arguments stay discrete argv entries (kills the injection).\n- Validate agentName against a strict allowlist (^[A-Za-z0-9._/-]+$).\n- Bind to loopback only (app.listen(PORT, '127.0.0.1', ...)).\n- Replace the wildcard CORS with a same-origin allowlist and reject other origins.","status":"published","published":"2026-09-03T19:50:47Z","modified":"2026-09-03T19:50:48Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-78","CWE-306","CWE-352"],"updated_at":"2026-11-02T14:41:11.621873Z"}],"nvd":[{"id":"CVE-2026-73222","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.","status":"published","published":"2026-08-11T19:18:51.72Z","modified":"2026-10-24T15:10:00.19Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-78","CWE-306","CWE-352"],"updated_at":"2026-11-02T14:12:36.880938Z"}],"osv":[{"id":"CVE-2026-73222","title":"Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)","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.","status":"published","published":"2026-08-11T18:27:09.297Z","modified":"2026-10-28T02:31:14.455122674Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-306","CWE-352","CWE-78"],"updated_at":"2026-11-02T15:45:15.88521Z"},{"id":"GHSA-79wm-x847-7cvg","title":"Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)","description":"### Summary\n`npx claude-code-templates --studio` launches \"Claude Code Studio\", an Express HTTP server (`cli-tool/src/sandbox-server.js`, default port 3444) that binds to **all interfaces** (`0.0.0.0`), sets `Access-Control-Allow-Origin: *`, and requires **no authentication**. Two POST endpoints pass attacker-controlled request-body fields into `child_process.spawn(..., { shell: true })`. Because `shell: true` makes Node join the argv array into a single `sh -c` string, the fields are parsed by the shell and metacharacters execute. Any unauthenticated attacker who can reach the port — a malicious web page the developer visits, or anyone on the same LAN — can execute arbitrary OS commands on the developer's machine.\n\n### Details\nIn `cli-tool/src/sandbox-server.js`:\n\n- `app.listen(PORT, ...)` is called with no host argument, so the server listens on `0.0.0.0` / `::` (reachable from the LAN, not just localhost).\n- The CORS middleware sends `Access-Control-Allow-Origin: *` and answers the preflight `OPTIONS` for any origin, so a browser will deliver cross-origin POSTs to it.\n- There is no authentication on any endpoint.\n\nThe vulnerable sinks:\n\n1. `POST /api/execute` — the `prompt` body field flows into `executeLocalTask()`:\n   ```js\n   const child = spawn('claude', [finalPrompt], { /* ... */ shell: true });\n   The only validation on prompt is a length check (\u003e= 10 chars). With shell: true, finalPrompt is interpreted by the shell.\n\n2. POST /api/install-agent — the agentName body field:\nconst child = spawn('npx', ['claude-code-templates@latest', '--agent', agentName, '--yes'], { /* ... */ shell: true });\n2. agentName is used unvalidated. (The same unsafe pattern is also reachable through /api/execute's agent field via checkAndInstallAgent().)\n\nRoot cause: spawn(cmd, argsArray, { shell: true }) does not keep argsArray as separate argv entries — Node builds cmd + ' ' + argsArray.join(' ') and runs it via sh -c, so every element is subject to shell parsing.\n\nPoC\n\n# Victim\nnpx claude-code-templates --studio          # server on 0.0.0.0:3444\n\n# Attacker (another LAN host, or a malicious web page fetch(), or locally)\ncurl -s -X POST http://127.0.0.1:3444/api/execute \\\n  -H 'Content-Type: application/json' \\\n  --data '{\"prompt\":\"aaaaaaaaaa; touch /tmp/CCT_RCE_PROOF\",\"mode\":\"local\"}'\n\ncurl -s -X POST http://127.0.0.1:3444/api/install-agent \\\n  -H 'Content-Type: application/json' \\\n  --data '{\"agentName\":\"x; touch /tmp/CCT_AGENT_PROOF #\"}'\n\nls -la /tmp/CCT_RCE_PROOF /tmp/CCT_AGENT_PROOF   # both created =\u003e injected commands ran\nThe aaaaaaaaaa padding satisfies the 10-char minimum, then ; (or $(...), or backticks) starts the injected command. claude/npx do not even need to be installed — the injected segment runs regardless.\n\nConfirmed at runtime on v1.28.13 (Node 22, Linux): both marker files were created, the server listened on *:3444, and an OPTIONS preflight from Origin: https://evil.example returned 200 with Access-Control-Allow-Origin: *.\n\nImpact\n\nUnauthenticated remote code execution (CWE-78) on any machine running --studio. Two reachability paths:\n- Drive-by: a developer running --studio who visits an attacker-controlled web page — the page's cross-origin fetch() (Content-Type application/json) passes the wildcard CORS preflight and delivers the POST, achieving RCE with no other interaction.\n- LAN: because the server binds 0.0.0.0, anyone on the same network (office, co-working space, public Wi-Fi) can hit port 3444 directly.\n\nImpact is full compromise of the developer's user account (arbitrary command execution with the developer's privileges): source code, SSH keys, cloud credentials, and .env secrets.\n\nSuggested fix\n\n- Remove shell: true from all three spawns so arguments stay discrete argv entries (kills the injection).\n- Validate agentName against a strict allowlist (^[A-Za-z0-9._/-]+$).\n- Bind to loopback only (app.listen(PORT, '127.0.0.1', ...)).\n- Replace the wildcard CORS with a same-origin allowlist and reject other origins.","status":"published","published":"2026-09-03T19:50:47Z","modified":"2026-09-03T20:00:04.931402692Z","cvss":[{"version":"3.1","score":8.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-306","CWE-352","CWE-78"],"updated_at":"2026-11-02T15:46:41.002603Z"}]}}