Summary
Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution
Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it.
Users on standard Claude Code auto-update have received this fix automatically. Users performing manual updates are advised to update to the latest version.
Thank you to hackerone.com/metnew for reporting this issue.
Impact
Input manipulates file paths to reach files outside the intended directory, such as configuration or credential files. Typical impact: unauthorized file read or write outside the intended directory.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2026-55607? CVE-2026-55607 is a high-severity path traversal vulnerability in @anthropic-ai/claude-code (npm), affecting versions >= 2.1.38, < 2.1.163. It is fixed in 2.1.163. Input manipulates file paths to reach files outside the intended directory, such as configuration or credential files.
- Which versions of @anthropic-ai/claude-code are affected by CVE-2026-55607? @anthropic-ai/claude-code (npm) versions >= 2.1.38, < 2.1.163 is affected.
- Is there a fix for CVE-2026-55607? Yes. CVE-2026-55607 is fixed in 2.1.163. Upgrade to this version or later.
- Is CVE-2026-55607 exploitable, and should I be worried? Whether CVE-2026-55607 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-55607 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-55607? Upgrade
@anthropic-ai/claude-codeto 2.1.163 or later.