CVE-2026-35022
Anthropic Claude Code & Agent SDK OS Command Injection via Authentication Helper
CVSS Score
9.8
EPSS Score
0.3%
EPSS Percentile
55th
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.
| CWE | CWE-78 |
| Vendor | anthropic |
| Product | claude code |
| Published | Apr 6, 2026 |
| Last Updated | Apr 13, 2026 |
Stay Ahead of the Next One
Get instant alerts for anthropic claude code
Be the first to know when new critical vulnerabilities affecting anthropic claude code are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
Affected Versions
Anthropic / Claude Code
0 ≤ 2.1.91
Anthropic / Claude Agent SDK for Python
0 ≤ 0.1.55
References
Credits
Francesco Cipollone