Claude Code echo command allowed bypass of user approval prompt for command execution

NGHIÊM TRỌNG 9.8CVE-2025-54795 · GHSA-x56v-x2h6-7j34 · Công bố 05/08/2025 · cập nhật 17/06/2026

Tóm tắt nhanh

CVE-2025-54795 là lỗ hổng mức NGHIÊM TRỌNG (CVSS 9.8) ảnh hưởng claude code (anthropic), @anthropic-ai/claude-code.
Xác suất bị khai thác trong 30 ngày tới (EPSS): 1.0%, cao hơn 64.1% các lỗ hổng khác.
Cách xử lý: cập nhật lên 1.0.20 hoặc mới hơn.

Gói / sản phẩm	Phiên bản bị ảnh hưởng	Phiên bản đã vá
claude code anthropic	`< 1.0.20`	`1.0.20`
@anthropic-ai/claude-code npm	`< 1.0.20`	`1.0.20`

Mô tả

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window.

Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.

Thank you to Elad Beber (Cymulate) for reporting this issue!

Mô tả của NVD

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.