Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code

CAO 7.5CVE-2025-55284 · GHSA-x5gv-jw7f-j6xj · Công bố 16/08/2025 · cập nhật 17/06/2026

Tóm tắt nhanh

CVE-2025-55284 là lỗ hổng mức CAO (CVSS 7.5) ảnh hưởng claude code (anthropic), @anthropic-ai/claude-code.
Xác suất bị khai thác trong 30 ngày tới (EPSS): 0.60%, cao hơn 48.5% các lỗ hổng khác.
Cách xử lý: cập nhật lên 1.0.4 hoặc mới hơn.

Gói / sản phẩm	Phiên bản bị ảnh hưởng	Phiên bản đã vá
claude code anthropic	`< 1.0.4`	`1.0.4`
@anthropic-ai/claude-code npm	`< 1.0.4`	`1.0.4`

Mô tả

Due to an overly broad allowlist of safe commands, it was possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation. 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 https://hackerone.com/wunderwuzzi23 for reporting this issue!

Mô tả của NVD

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. 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.