RCE in Anthropic Claude Code
CVE-2025-66032
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.
Vulnerability class: Command Injection (OS Command Injection)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS: 0.007 (50.8th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 51st percentile — 50.8% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.007 · newest: 0.007 · change: 0.000
Affected products
- Anthropic Claude Code
- Anthropics Claude-Code — versions < 1.0.93
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2025-66032?
- CVE-2025-66032 is a critical-severity vulnerability in Anthropic Claude Code, classified under Command Injection. CVSS score: 9.8/10. Published 2025-12-03.
- How severe is CVE-2025-66032?
- Critical severity. CVSS v3 base score is 9.8 out of 10.