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.
Cite this page
CVE-2026-35022. CVEDatabase.com. Retrieved 3 May 2026. https://cvedatabase.com/cve/CVE-2026-35022
Use CWE-78, Anthropic vendor hub and Claude Agent Sdk product page to widen CVE-2026-35022 into its surrounding weakness, vendor, and product context.
Compare it with CVE-2026-35020 and CVE-2026-35021 for nearby disclosures in the same product family.