Claude Code has a Command Injection in find Command Bypasses User Approval Prompt
Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window.
Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.
Claude Code thanks https://hackerone.com/alexbernier for reporting this issue!
Affected software
Click a technology to see all vulnerabilities affecting it.
| Platform | Package | Vulnerable versions | Fixed in |
|---|---|---|---|
| npm package | @anthropic-ai/claude-code | < 2.0.72 | 2.0.72 |
References
- CVSS vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N- Weakness (CWE)
CWE-78, CWE-94- Platform
- npm
- Package
@anthropic-ai/claude-code- Disclosed
- 03.02.2026
- Updated
- 11.10.2026 10:22
Sources and licenses
OSV / GitHub Advisory Database - GHSA-qgqw-h4xq-7w8w - CC BY 4.0
Vulnerability history: @anthropic-ai/claude-code
All published vulnerabilities of this package (npm package), newest first. Shows whether this is a one-off slip or a package that needs watching.
- Total entries
- 29
- First → latest
- 06.2025 10.2026
- Without a fix
- 0
- Exploited in attacks
- 0
Severity breakdown
- High 23
- Medium 4
- Low 2
Disclosures per year
- 2025: 13
- 2026: 16
-
Claude Code has a Command Injection in find Command Bypasses User Approval Prompt this entry
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.