Headline
GHSA-qxfv-fcpc-w36x: Claude Code rg vulnerability does not protect against approval prompt bypass
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!
- GitHub Advisory Database
- GitHub Reviewed
- CVE-2025-58764
Claude Code rg vulnerability does not protect against approval prompt bypass
High severity GitHub Reviewed Published Sep 9, 2025 in anthropics/claude-code • Updated Sep 10, 2025
Package
npm @anthropic-ai/claude-code (npm)
Affected versions
< 1.0.105
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!
References
- GHSA-qxfv-fcpc-w36x
Published to the GitHub Advisory Database
Sep 10, 2025
Last updated
Sep 10, 2025