Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Claude Code

CVE-2026-25723: Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions

highCVSS 4.0 7.7GHSA-mhg7-666j-cqg4

Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled.

Published Feb 6, 2026

Affected packages

@anthropic-ai/claude-code

Ecosystem
npm
Affected
< 2.0.55
Fixed in
2.0.55
Check
npm ls @anthropic-ai/claude-code

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled.

Users on standard Claude Code auto-update received this fix automatically. Users performing manual updates are advised to update to the latest version.

Claude Code thanks hackerone.com/nil221 for reporting this issue!

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Claude Code vulnerabilities

All Claude Code entries