Skip to content

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

HighCVSS 7.7 EPSS 0.64%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: no · technical impact: total

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.

Upgrade path

3 packages: 2 fixed.

PackageAffectedFixed inStatus
Anthropic claude code < 2.0.72 2.0.72 Fixed
anthropic-ai @anthropic-ai/claude-code(npm) < 2.0.72 2.0.72 Fixed
anthropics claude-code = < 2.0.72 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
anthropics claude-code = < 2.0.72 No fix listed
anthropic-ai @anthropic-ai/claude-code(npm) < 2.0.72 2.0.72
Anthropic claude code < 2.0.72 2.0.72

References