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.
Problem types
CWE-78 Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Product status
Any version
Any version
Credits
Francesco Cipollone
References
phoenix.security/...-code-cli-allow-credential-exfiltration/
www.vulncheck.com/...and-injection-via-authentication-helper