Skip to content

CVE-2026-55607 Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution

HighCVSS 7.7 EPSS 0.69%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: no · technical impact: total
Technology
Red Hat

Description

Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, 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. This vulnerability is fixed in 2.1.163.

Upgrade path

4 packages: 2 fixed, 1 with no fix yet.

PackageAffectedFixed inStatus
redhat/openshift-lightspeed/lightspeed-agentic-sandbox-rhel9(Red Hat openshift_lightspeed 1) All versions No fix listed No fix yet
Anthropic claude code >= 2.1.38, < 2.1.163 2.1.163 Fixed
anthropic-ai @anthropic-ai/claude-code(npm) >= 2.1.38, < 2.1.163 2.1.163 Fixed
anthropics claude-code = >= 2.1.38, < 2.1.163 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
anthropics claude-code = >= 2.1.38, < 2.1.163 No fix listed
redhat/openshift-lightspeed/lightspeed-agentic-sandbox-rhel9(Red Hat:openshift_lightspeed:1) All versions No fix listed
anthropic-ai @anthropic-ai/claude-code(npm) >= 2.1.38, < 2.1.163 2.1.163
Anthropic claude code >= 2.1.38, < 2.1.163 2.1.163

References