Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
anthropics claude-code
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Claude Code是Anthropic开源的一个终端原生AI编程工具。 Claude Code 2.0.55之前版本存在操作系统命令注入漏洞，该漏洞源于未能正确验证使用带echo命令的管道sed操作的命令，可能导致绕过文件写入限制。

AI Predicted 7.8 Difficulty: Moderate EPSS 0.48% · P39

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-25723

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions
Source: CVE Program / CVE List V5
Vulnerability Description
Claude Code is an agentic coding tool. Prior to version 2.0.55, 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. This issue has been patched in version 2.0.55.
Source: CVE Program / CVE List V5
CVSS Information
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
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
Claude Code 操作系统命令注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Claude Code是Anthropic开源的一个终端原生AI编程工具。 Claude Code 2.0.55之前版本存在操作系统命令注入漏洞，该漏洞源于未能正确验证使用带echo命令的管道sed操作的命令，可能导致绕过文件写入限制。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
anthropics claude-code < 2.0.55 -

II. Public POCs for CVE-2026-25723

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-25723

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-25723 (1)

Same Patch Batch · anthropics · 2026-02-06 · 4 CVEs total

CVE-2026-25722 Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection
CVE-2026-25725 Claude Code Has Sandbox Escape via Persistent Configuration Injection in settings.json
CVE-2026-25724 Claude Code Has Permission Deny Bypass Through Symbolic Links

IV. Related Vulnerabilities

Same product: claude-code
Same vendor: anthropics
Same weakness: CWE-20

V. Comments for CVE-2026-25723

No comments yet

Leave a comment