Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
📦 npm
Not in CISA KEV

CVE-2026-55607

CVE-2026-55607 is a Path Traversal vulnerability in @anthropic-ai/claude-code. O3 Security confirms whether CVE-2026-55607 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution

Also known asGHSA-7835-87q9-rgvv
Published
Jun 29, 2026
Updated
Aug 12, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Aug 12, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Real-World Exposure

1 pkg affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, a proxy for how much of the ecosystem is exposed.

@anthropic-ai/claude-codenpm
11.4Mdownloads / week

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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
📦npm@anthropic-ai/claude-code2.1.38&&< 2.1.1632.1.163

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update @anthropic-ai/claude-code to 2.1.163 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-55607 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2026-55607 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2026-55607. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

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
O3 Security · Impact-Aware SCA

Is CVE-2026-55607 in your dependencies?

O3 detects CVE-2026-55607 across npm dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.