High severityNVD Advisory· Published Dec 3, 2025· Updated Dec 3, 2025
Claude Code Command Validation Bypass Allows Arbitrary Code Execution
CVE-2025-66032
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.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
@anthropic-ai/claude-codenpm | < 1.0.93 | 1.0.93 |
Affected products
1- Range: < 1.0.93
Patches
0No patches discovered yet.
Vulnerability mechanics
AI mechanics synthesis has not run for this CVE yet.
References
3- github.com/advisories/GHSA-xq4m-mc3c-vvg3ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2025-66032ghsaADVISORY
- github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3ghsax_refsource_CONFIRMWEB
News mentions
0No linked articles in our index yet.