Claude Code has a Command Injection in find Command Bypasses User Approval Prompt
No sign of exploitation. No public exploitation artifact known so far.
Claude Code had a flaw that let attackers bypass the safety confirmation prompt by sneaking malicious commands into the find command, allowing untrusted code to run without user approval. This matters because it undermines the built-in protections designed to prevent accidental execution of harmful operations.
A command parsing vulnerability in Claude Code prior to version 2.0.72 allowed command injection through the find command, enabling attackers to circumvent the confirmation prompt (CWE-78, CWE-94). The attack vector required injecting untrusted content into the Claude Code context window; successful exploitation resulted in arbitrary command execution without user consent.