8.7High

CVE-2025-58764Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution

anthropics claude-code Published: (1 year ago)

Description

Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to version 1.0.105 or the latest version.

Weakness (CWE): CWE-94

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
anthropic claude code < 1.0.105
anthropics claude-code < 1.0.105

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* < 1.0.105