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 Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Anthropic | Claude Agent Sdk | <= 0.1.55 |
| Anthropic | Claude Code | <= 2.1.91 |
Related Weaknesses (CWE)
References
- https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-cExploitThird Party Advisory
- https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-Third Party Advisory
FAQ
What is CVE-2026-35022?
CVE-2026-35022 is a vulnerability with a CVSS score of 9.8 (CRITICAL). 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 ...
How severe is CVE-2026-35022?
CVE-2026-35022 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-35022?
Check the references section above for vendor advisories and patch information. Affected products include: Anthropic Claude Agent Sdk, Anthropic Claude Code.