Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS 4.0

7.7 · CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N · score source

EPSS

• CVE-2026-25722: 0.51% estimated exploitation activity in the next 30 days; percentile 43.52 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protection and create or modify files without user confirmation. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically. Users performing manual updates are advised to update to the latest version. About Claude Code thanks hackerone.com/nil221 for reporting this issue!

Published by the source

6 Feb 2026, 19:02 UTC

Last modified by the source

6 Feb 2026, 19:56 UTC

Source last checked

26 Oct 2026, 12:42 UTC

1. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-66q4-vfjg-2qhh

2. Revision 2 · amended · 24 Oct 2026

   Reviewed OSV alias/range/CVSS4 correction; package source scopes and original publication preserved. No customer finding resolved.

3. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-66q4-vfjg-2qhh

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-25722

Advisory: Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection
IDs: CVE-2026-25722, GHSA-66q4-vfjg-2qhh
Record: https://patchnext.com/advisories/cve-2026-25722 (revision 3, source checked 26 Oct 2026, 12:42 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 7.7)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: @anthropic-ai/claude-code 2.0.57. A vendor fix does not mean a deployment is fixed.

## Affected components
- npm @anthropic-ai/claude-code: affected < 2.0.57; fixed in 2.0.57

## Suggested inspection (read-only)
- `npm ls @anthropic-ai/claude-code --all`: lists every installed copy and version, including transitive ones. Run in the project root after `npm ci`.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on @anthropic-ai/claude-code.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-66q4-vfjg-2qhh (OSV record GHSA-66q4-vfjg-2qhh lists affected ranges: npm @anthropic-ai/claude-code >=0 <2.0.57 (fixed))
- Verified: https://github.com/advisories/GHSA-66q4-vfjg-2qhh (GitHub-reviewed advisory GHSA-66q4-vfjg-2qhh lists affected ranges: npm @anthropic-ai/claude-code >=0 <2.0.57)

Commands are suggestions: review each one before running it.