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.
Details
Affected Packages
| Software | From version | Fixed in |
|---|---|---|
| claude-agent-sdk | — | 0.1.55 |
| claude-code | — | 2.1.91 |
| unknown | — | — |
References
N/ASimilar Threats
- High CVE-2026-35020
- High CVE-2026-35021
Patch Gap Protection
Running software with known vulnerabilities?
BotEraser can help reduce exposure by blocking IPs associated with exploit activity — even before a patch is available.
Start Free →No credit card required · Results in minutes
ⓘ Data Notice: The information presented above has been compiled from publicly available internet sources. Boteraser aggregates this data solely for informational purposes and does not independently classify, evaluate, or endorse any findings about the vulnerabilities listed. The accuracy and completeness of this information is the sole responsibility of the original publishers. Boteraser and its operators accept no liability for any decisions made based on this data.