GitHub Advisoryadvisory · npm

GHSA-qgqw-h4xq-7w8w Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

HIGH Published 2026-02-03 Modified 2026-02-03 Official page ↗
Aliases
CVE-2026-24887
Ecosystem
npm
Packages
@anthropic-ai/claude-code
Severity
High
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
Weaknesses
CWE-78, CWE-94
Reviewed
2026-02-03

Affected packages

• npm @anthropic-ai/claude-code: < 2.0.72 → fixed in 2.0.72

Description

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!

Related

Alias · CVE (1)

Weakness · CWE (2)

  • CWE-78 Improper Neutralization of Special Elements used in an OS Command weakness
  • CWE-94 Improper Control of Generation of Code weakness

References