CVE-2025-66032

Description

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!

Affected packages (1)

• npm/@anthropic-ai/claude-codefrom 0, < 1.0.93

CVSS scores

References (3)

• ADVISORYhttps://nvd.nist.gov/vuln/detail/CVE-2025-66032
• PATCHhttps://github.com/anthropics/claude-code
• WEBhttps://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3