CodexGuild Knowledge Base

Claude Code rg vulnerability does not protect against approval prompt bypass

as of Sep 10, 2025 · applies to @anthropic-ai/claude-code < 1.0.105 · canonical · codexguild.com/kb/ghsa-qxfv-fcpc-w36x · exported 2026-10-11

Canonical as of Sep 10, 2025

Claude Code rg vulnerability does not protect against approval prompt bypass

High severity. Affects @anthropic-ai/claude-code < 1.0.105. Upgrade to 1.0.105 or later.

CVE-2025-58764 / GHSA-qxfv-fcpc-w36x · severity: high · npm

Affected

@anthropic-ai/claude-code < 1.0.105 → fixed in 1.0.105

Details

Due to an error in command parsing, it was possible to bypass 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 the latest version.

Thank you to the NVIDIA AI Red Team for reporting this issue!

Source: GHSA-qxfv-fcpc-w36x — GitHub Advisory Database (CC-BY-4.0).