HIGH

GHSA-qxfv-fcpc-w36x

Claude Code rg vulnerability does not protect against approval prompt bypass

Quick fix

GHSA-qxfv-fcpc-w36x — @anthropic-ai/claude-code: upgrade to the fixed version with the command below.

npm install @anthropic-ai/claude-code@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!

Are you affected?

Enter the version of the package you're using.

Affected packages

npm/@anthropic-ai/claude-code

Introduced in: 0Fixed in: 1.0.105

Fixnpm install @anthropic-ai/claude-code@1.0.105

References

https://github.com/anthropics/claude-code/security/advisories/GHSA-qxfv-fcpc-w36x[WEB]
https://nvd.nist.gov/vuln/detail/CVE-2025-58764[ADVISORY]
https://github.com/anthropics/claude-code[PACKAGE]