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

CVE-2025-66032: Claude Code Command Validation Bypass Allows Arbitrary Code Execution

highCVSS 4.0 8.7GHSA-xq4m-mc3c-vvg3

Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already.

Published Dec 3, 2025 · Updated Dec 4, 2025

Affected packages

@anthropic-ai/claude-code

Ecosystem
npm
Affected
< 1.0.93
Fixed in
1.0.93
Check
npm ls @anthropic-ai/claude-code

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window.

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

Thank you to [RyotaK](hxxps://ryotak.net) from [GMO Flatt Security Inc.](hxxps://flatt.tech/en/) for reporting this issue!

Credited to Ry0taK.

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