CVE-2025-58764
CRITICALClaude Code < 1.0.105 - Command Injection via Confirmation Prompt Bypass
Title source: llmDescription
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.
References (1)
Core 1
Core References
Vendor Advisory x_refsource_confirm
https://github.com/anthropics/claude-code/security/advisories/GHSA-qxfv-fcpc-w36x
Scores
CVSS v3
9.8
EPSS
0.0051
EPSS Percentile
39.6%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA SSVC
Vulnrichment
Exploitation
none
Automatable
yes
Technical Impact
total
Details
CWE
CWE-94
Status
published
Products (2)
anthropic/claude_code
< 1.0.105
anthropic-ai/claude-code
0 - 1.0.105npm
Published
Sep 10, 2025
Tracked Since
Feb 18, 2026