Advisory

GHSA-qxfv-fcpc-w36x

Also known as: CVE-2025-58764

Summary

Claude Code rg vulnerability does not protect against approval prompt bypass

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!

Severity

High Basis: The source's own band: HIGH

Dates

Published
2025-09-10 17:10 UTC
Modified
2025-09-10 21:14 UTC

Affected packages and fixes

@anthropic-ai/claude-code

npm · All systems

Affected

  • introduced 0, fixed 1.0.105 (semver)

Fixed versions

1.0.105

Fix

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences