Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Claude Code

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

highCVSS 4.0 8.7GHSA-qxfv-fcpc-w36x

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.

Published Sep 10, 2025

Affected packages

@anthropic-ai/claude-code

Ecosystem
npm
Affected
< 1.0.105
Fixed in
1.0.105
Check
npm ls @anthropic-ai/claude-code

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

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

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More Claude Code vulnerabilities

All Claude Code entries