CVE-2026-35022:
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.
Score
A numerical rating that indicates how dangerous this vulnerability is.
9.8Critical- Published Date:Apr 6, 2026
- CISA KEV Date:*No Data*
- Industries Affected:20
Threat Predictions
- EPSS Score:0.2
- EPSS Percentile:48%
Exploitability
- Score:3.9
- Attack Vector:NETWORK
- Attack Complexity:LOW
- Privileges Required:NONE
- User Interaction:NONE
- Scope:UNCHANGED
Impact
- Score:5.9
- Confidentiality Impact:HIGH
- Integrity Impact:HIGH
- Availability Impact:HIGH
Description Preview
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.
Industries Affected
Below is a list of industries most commonly impacted or potentially at risk based on intelligence.
