How severe is CVE-2026-55607?

No CVSS score has been assigned to CVE-2026-55607 yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by CVE-2026-55607?

CVE-2026-55607 affects the following packages: @anthropic-ai/claude-code (npm). Ecosystems affected: npm.

How do I fix CVE-2026-55607?

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.

How do I detect CVE-2026-55607 in my npm dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate CVE-2026-55607 if there is no patch (or I can't update yet)?

Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Is CVE-2026-55607 actively exploited in the wild?

No public exploit code has been indexed for CVE-2026-55607 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2026-55607?

CVE-2026-55607 has an EPSS (Exploit Prediction Scoring System) score of 0.7%, placing it in the 51th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is CVE-2026-55607?

CVE-2026-55607 is classified as Path Traversal (CWE-22), CWE-59 (CWE-59), OS Command Injection (CWE-78). These weakness types describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation. This is a high-impact weakness class that often enables remote code execution or data exposure.

When was CVE-2026-55607 published, and has it been updated?

CVE-2026-55607 was published on June 29, 2026 and was last updated on August 12, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

CVE-2026-55607: @anthropic-ai/claude-code

Exploitation Status

No confirmed exploitation observed yet

A successful exploit gives an attacker total control of the affected component, not partial access.
CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-55607.

EPSS Exploitation Probability

via FIRST.org ↗

0.7%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs51th percentile — riskier than 51% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, and reverse-dependency count shows how many other packages break if it stays unpatched.

277other npm packages depend on this — each one inherits the vulnerability until it's patched upstream

@anthropic-ai/claude-codenpm

13.3Mdownloads / week

Description

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.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
📦npm	`@anthropic-ai/claude-code`	≥ 2.1.38&&< 2.1.163	2.1.163`npm install @anthropic-ai/claude-code@2.1.163`

Affected Products

1 product · 1 configurations

Application

claude codeanthropic

≥ 2.1.38 && < 2.1.163

range

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
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.
Workarounds
Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatImportant

This is an Important vulnerability in Claude Code, an agentic coding tool within OpenShift Lightspeed, stemming from a git directory confusion flaw. The vulnerability allows an attacker to overwrite user configuration files, leading to arbitrary code execution outside of sandbox restrictions. Exploitation requires a…

Workaround published by Red Hat

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

Source: Red Hat security advisory for CVE-2026-55607 (CC BY 4.0)

Frequently Asked Questions

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

O3 Security · Impact-Aware SCA

Is CVE-2026-55607 in your dependencies?

Find it across npm, including transitive dependencies.

Scan my dependencies How O3 SCA works

CVE-2026-55607 — @anthropic-ai/claude-code