Advisory Database
  • Advisories
  • Dependency Scanning
  1. npm
  2. ›
  3. @anthropic-ai/claude-code
  4. ›
  5. CVE-2025-58764

CVE-2025-58764: Claude Code rg vulnerability does not protect against approval prompt bypass

September 10, 2025

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

  • github.com/advisories/GHSA-qxfv-fcpc-w36x
  • github.com/anthropics/claude-code
  • github.com/anthropics/claude-code/security/advisories/GHSA-qxfv-fcpc-w36x
  • nvd.nist.gov/vuln/detail/CVE-2025-58764

Code Behaviors & Features

Detect and mitigate CVE-2025-58764 with GitLab Dependency Scanning

Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →

Affected versions

All versions before 1.0.105

Fixed versions

  • 1.0.105

Solution

Upgrade to version 1.0.105 or above.

Weakness

  • CWE-94: Improper Control of Generation of Code ('Code Injection')

Source file

npm/@anthropic-ai/claude-code/CVE-2025-58764.yml

Spotted a mistake? Edit the file on GitLab.

  • Site Repo
  • About GitLab
  • Terms
  • Privacy Statement
  • Contact

Page generated Wed, 24 Sep 2025 12:18:51 +0000.