Command Injection Affecting @anthropic-ai/claude-code package, versions <2.0.55
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-JS-ANTHROPICAICLAUDECODE-15248308
- published8 Feb 2026
- disclosed6 Feb 2026
- credithackerone.com/nil221
Introduced: 6 Feb 2026
CVE-2026-25723 (opens in a new tab)How to fix?
Upgrade @anthropic-ai/claude-code to version 2.0.55 or higher.
Overview
@anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.
Affected versions of this package are vulnerable to Command Injection via improper validation of commands containing piped sed operations with the echo command. An attacker can execute arbitrary system commands and write to sensitive directories by crafting malicious input, bypassing file write restrictions.
Note: This is only exploitable if the accept edits feature is enabled.