AI and data stack advisories

Severe, 6 weeks1496Projects326

1496 severe, 6 weeks · 326 projects

AnthropicGHSA-66q4-vfjg-2qhh

Command Injection via Directory Change Bypasses Write Protection

Anthropic

CVE-2026-25722 · Published Feb 6, 2026

High7.7
Fix: upgrade to v2.0.57 or later
GitHub advisory

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.

Thank you to hackerone.com/nil221 for reporting this issue!

Affected versions

PackageAffectedFixed in
@anthropic-ai/claude-code
npm
< v2.0.57v2.0.57
Details and references
CVSS 4.0
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
Severity from
GitHub (reviewed advisory)
Weakness
CWE-20, CWE-78

More Anthropic advisories

All Anthropic