CVE-2026-35022

critical
Published 2026-04-06 · Modified 2026-04-29
CVSS v3
9.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS v2
VIR risk
9.8

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.

Predictions

Exploit likelihood
97%
Patch ETA

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No vendor mitigations ingested yet for this CVE. The mitigation-content worker queues fetches as references arrive — check back in a few minutes, or see the references list below.

Application impact

VendorProductVersionsFixed
anthropicclaude_agent_sdk{"endIncluding":"0.1.55"}
anthropicclaude_code{"endIncluding":"2.1.91"}

References

CWEs

CWE-78

Verify integrity in audit chain (admin only). AS-IS.