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.
Cite this page
CVE-2026-35020. CVEDatabase.com. Retrieved 1 May 2026. https://cvedatabase.com/cve/CVE-2026-35020
Use CWE-78, Anthropic vendor hub and Claude Agent Sdk product page to widen CVE-2026-35020 into its surrounding weakness, vendor, and product context.
Compare it with CVE-2026-35022 and CVE-2026-35021 for nearby disclosures in the same product family.