CVE-2026-24887: Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Severity: high (CVSS 8.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.7% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-02-03 · updated 2026-06-17
Weakness: CWE-78

Description

Claude Code is an agentic coding tool. Prior to version 2.0.72, 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. This issue has been patched in version 2.0.72.

Affected products

anthropics claude-code: before 2.0.72 — fixed in 2.0.72

How to fix

Upgrade to a fixed version: anthropics claude-code 2.0.72. Check the vendor advisory for mitigations.

References

https://github.com/anthropics/claude-code/security/advisories/GHSA-qgqw-h4xq-7w8w

Get alerted when CVE-2026-24887 or the next vulnerability affects your stack