Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)
Affects claude-code-templatesSource GCVE Database
Not known to be exploited · CVSS 8.8 High : upgrade to 1.29.4 soon.
Data as of 4 Nov 2026, 20:36 UTC
- EPSS
- 0.3% chance of exploitation in 30 days – higher than 25% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 1.29.4
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 11 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 4 Nov 2026.
What to do
Upgrade claude-code-templates to 1.29.4.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
Homebrewclaude-code-templatespkg:brew/claude-code-templatesOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
A fix is available in version 1.29.4. Users should upgrade to 1.29.4 or later. The vendor recommends removing shell: true from all child_process.spawn calls to prevent shell injection, validating input fields against strict allowlists, binding the server to the loopback interface only (127.0.0.1), and replacing the wildcard CORS policy with a same-origin allowlist. Until patched, restrict network access to port 3444 to trusted users only.
Description
Claude Code Studio server (part of claude-code-templates) versions >=1.27.0 and <1.29.4 contain an unauthenticated remote code execution vulnerability. The server listens on all interfaces without authentication and allows cross-origin POST requests. Two POST endpoints pass attacker-controlled input directly into shell commands with shell: true, enabling arbitrary OS command execution by unauthenticated attackers who can reach the server port. This can lead to full compromise of the developer's user account.
References
- github.com/davila7/claude-code-templates/security/advisories/GHSA-79wm-x847-7cvg (opens in a new tab)
- nvd.nist.gov/vuln/detail/CVE-2026-73222 (opens in a new tab)
- github.com/davila7/claude-code-templates/commit/bc4618b07232633c1c0aac12a43e436268d31783 (opens in a new tab)
- github.com/davila7/claude-code-templates (opens in a new tab)
- github.com/davila7/claude-code-templates/blob/main/CHANGELOG.md (opens in a new tab)