Claude Code vulnerable to command execution prior to startup trust dialog

緊急 9.8CVE-2025-65099 · GHSA-5hhx-v7f6-x7gv · 19/11/2025 公開 · 18/10/2026 更新

要点

CVE-2025-65099 は claude code (anthropic), @anthropic-ai/claude-code に影響する深刻度「緊急」 (CVSS 9.8) の脆弱性です。
今後30日間に悪用される確率（EPSS）：0.55%（全脆弱性の 45.7% より高い）。
対処：1.0.39 以降に更新してください。

パッケージ	影響を受けるバージョン	修正済みバージョン
claude code anthropic	`< 1.0.39`	`1.0.39`
@anthropic-ai/claude-code npm	`< 1.0.39`	`1.0.39`

概要

When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.

Thank you to Benjamin Faller, Redguard AG and Michael Hess for reporting this issue!

NVD の説明

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a user to start Claude Code in an untrusted directory and to be using Yarn 3.0 or above. This issue has been patched in version 1.0.39.