Skip to content

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

HighCVSS 8.7 EPSS 0.55%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: yes · technical impact: total

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.

Upgrade path

3 packages: 2 fixed.

PackageAffectedFixed inStatus
Anthropic claude code < 1.0.105 1.0.105 Fixed
anthropic-ai @anthropic-ai/claude-code(npm) < 1.0.105 1.0.105 Fixed
anthropics claude-code = < 1.0.105 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
anthropic-ai @anthropic-ai/claude-code(npm) < 1.0.105 1.0.105
anthropics claude-code = < 1.0.105 No fix listed
Anthropic claude code < 1.0.105 1.0.105

References