漏洞信息
尽管我们使用了先进的大模型技术，但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性，但请您根据实际情况进行核实和判断。
Vulnerability Title
Anthropic Claude Code & Agent SDK OS Command Injection via Authentication Helper
Vulnerability Description
Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in authentication helper execution where helper configuration values are executed using shell=true without input validation. Attackers who can influence authentication settings can inject shell metacharacters through parameters like apiKeyHelper, awsAuthRefresh, awsCredentialExport, and gcpAuthRefresh to execute arbitrary commands with the privileges of the user or automation environment, enabling credential theft and environment variable exfiltration.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability Type
OS命令中使用的特殊元素转义处理不恰当(OS命令注入)
Vulnerability Title
Claude Code CLI和Claude Agent SDK 操作系统命令注入漏洞
Vulnerability Description
Claude Code CLI和Claude Agent SDK都是Anthropic开源的产品。Claude Code CLI是一个命令行AI编码助手工具。Claude Agent SDK是一个AI编码助手开发者工具包。 Claude Code CLI和Claude Agent SDK存在操作系统命令注入漏洞，该漏洞源于身份验证助手执行中的操作系统命令注入，其中助手配置值使用shell=true执行且未进行输入验证，可能导致攻击者注入shell元字符执行任意命令。
CVSS Information
N/A
Vulnerability Type
N/A