CVE-2025-66032
Critical
Description
Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 1.0.93.
SeverityCritical
CVSS9.8
Exploit probability—
Product
Anthropic Claude Code
PublishedDec 3, 2025
First seenDec 3, 2025
Weakness typeCWE-77Command injection
How to fix
Update
- anthropic claude_code1.0.93 or later
- @anthropic-ai/claude-code1.0.93 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| anthropic claude_code | v < 1.0.93 | 1.0.93 |
| @anthropic-ai/claude-codenpm | v < 1.0.93 | 1.0.93 |
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.