HIGH · 8.4

CVE-2026-35020

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitra...

Vulnerability Description

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitrary commands by manipulating the TERMINAL environment variable. Attackers can inject shell metacharacters into the TERMINAL variable which are interpreted by /bin/sh when the command lookup helper constructs and executes shell commands with shell=true. The vulnerability can be triggered during normal CLI execution as well as via the deep-link handler path, resulting in arbitrary command execution with the privileges of the user running the CLI.

CVSS Score

8.4

HIGH

CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH

Affected Products

VendorProductVersions
AnthropicClaude Agent Sdk<= 0.1.55
AnthropicClaude Code<= 2.1.91

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-35020?

CVE-2026-35020 is a vulnerability with a CVSS score of 8.4 (HIGH). Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the command lookup helper and deep-link terminal launcher that allows local attackers to execute arbitra...

How severe is CVE-2026-35020?

CVE-2026-35020 has been rated HIGH with a CVSS base score of 8.4/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-35020?

Check the references section above for vendor advisories and patch information. Affected products include: Anthropic Claude Agent Sdk, Anthropic Claude Code.