AI and data stack advisories

Severe, 6 weeks1496Projects326

1496 severe, 6 weeks · 326 projects

AnthropicGHSA-qgqw-h4xq-7w8w

Command Injection in find Command Bypasses User Approval Prompt

Anthropic

CVE-2026-24887 · Published Feb 3, 2026

High7.7
Fix: upgrade to v2.0.72 or later
GitHub advisory

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.

Thank you to https://hackerone.com/alexbernier for reporting this issue!

Affected versions

PackageAffectedFixed in
@anthropic-ai/claude-code
npm
< v2.0.72v2.0.72
Details and references
CVSS 4.0
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
Severity from
GitHub (reviewed advisory)
Weakness
CWE-78, CWE-94

More Anthropic advisories

All Anthropic