Paper/Archive/CVE-2025-58764

CVE-2025-58764

anthropics claude-code — Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution

EPSS 0.5%CVSS 9.8

critical.is priorityof 100

CVSS 9.8 (NVD)9.8 / 10 × 3029.4 Not in CISA KEV+300.0 EPSS percentile 46.0.460 × 209.2 No public exploit+100.0 SSVC exploitation: none+100.0

Description · from the CVE record

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

ProductAffectedFixed inSource

claude-code< 1.0.105–CNA

Scores by source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

GitHub_M (CNA)8.7CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CISA ADPSSVCExploitation: none · Automatable: yes · Technical impact: total

References

refgithub.com/anthropics/claude-code/security/advisories/GHSA-qxfv-fcpc-w36x