CVE-2025-58764: high-severity vulnerability in anthropics claude-code
Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
No sign of exploitation. No public exploitation artifact known so far.
Claude Code versions before 1.0.105 had a flaw that allowed attackers to bypass the safety confirmation prompt and execute commands without user approval. This is dangerous because malicious code could run secretly on your system.
A command parsing error in Claude Code (CWE-94: Code Injection) allowed attackers to craft specially formatted input that bypassed the confirmation prompt mechanism, enabling execution of arbitrary commands. Exploitation requires injecting untrusted content into the Claude Code context; the vulnerability affects versions prior to 1.0.105.
In the same product, most dangerous first.