Skip to content
OpenAdvisories
High · 8.7 CVE-2025-58764 EUVD-2025-27564GHSA-qxfv-fcpc-w36x

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

Published Sep 10, 2025 · Updated Sep 11, 2025 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
anthropics claude-code < 1.0.105 —

Affected packages

EcosystemPackageAffectedFixedRecord
npm @anthropic-ai/claude-code < 1.0.105 1.0.105 GHSA-qxfv-fcpc-w36x

References