CVE-2026-24887
High
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.
SeverityHigh
CVSS8.8
Exploit probability—
Product
Anthropic Claude Code
PublishedFeb 3, 2026
First seenFeb 3, 2026
Weakness typeCWE-78OS command injectionCWE-94Code injection
How to fix
Update
- anthropic claude_code2.0.72 or later
- @anthropic-ai/claude-code2.0.72 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| anthropic claude_code | v < 2.0.72 | 2.0.72 |
| @anthropic-ai/claude-codenpm | v < 2.0.72 | 2.0.72 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
In the Intelligence 360 plan
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.