Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

CAO 8.8CVE-2026-33068 · GHSA-mmgp-wc2j-qcv7 · Công bố 20/03/2026 · cập nhật 17/06/2026

Tóm tắt nhanh

CVE-2026-33068 là lỗ hổng mức CAO (CVSS 8.8) ảnh hưởng claude code (anthropic), @anthropic-ai/claude-code.
Xác suất bị khai thác trong 30 ngày tới (EPSS): 0.34%, cao hơn 27.9% các lỗ hổng khác.
Cách xử lý: cập nhật lên 2.1.53 hoặc mới hơn.

Gói / sản phẩm	Phiên bản bị ảnh hưởng	Phiên bản đã vá
claude code anthropic	`< 2.1.53`	`2.1.53`
@anthropic-ai/claude-code npm	`< 2.1.53`	`2.1.53`

Mô tả

Claude Code resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent.

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 hackerone.com/cantina_xyz for reporting this issue.

Mô tả của NVD

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.

Tham khảo

anthropics/claude-code security advisory · WEB
nvd.nist.gov/vuln/detail/CVE-2026-33068 · ADVISORY
anthropics/claude-code · PACKAGE

Lỗ hổng khác của claude code

Xem tất cả →

Bạn đang dùng một trong các sản phẩm này? Quét site để biết có đang lộ phiên bản có lỗ hổng không.

Quét site miễn phí

Gói / sản phẩm

Phiên bản bị ảnh hưởng

Phiên bản đã vá

claude code

anthropic

< 2.1.53

2.1.53

@anthropic-ai/claude-code

npm