Claude Code Command Validation Bypass Allows Arbitrary Code Execution
Priority HIGH 73CWE-77Published · Updated
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Passive
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-77.
Summary
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.
Why it matters now
Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00738 54th percentileScored 2026-11-07
Fix Fixed claude-code (anthropics): 1.0.93@anthropic-ai/claude-code (npm): 1.0.93
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| anthropics | claude-code | before 1.0.93 | 1.0.93 | Patch available | CNA |
| — | @anthropic-ai/claude-code (npm) | before 1.0.93 | 1.0.93 | Patch available | GHSA-xq4m-mc3c-vvg3 |
- claude-code Vendoranthropics Affected before 1.0.93 Fixed in 1.0.93 Patch available CNA
- @anthropic-ai/claude-code (npm) Vendor— Affected before 1.0.93 Fixed in 1.0.93 Patch available GHSA-xq4m-mc3c-vvg3
CPE configurations NVD · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* | before 1.0.93 | Vulnerable | anthropics |
- cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* Versions before 1.0.93 Vulnerable ·anthropics
Remediation
- Fix · CNA claude-code (anthropics) Fixed in 1.0.93
- Fix · GHSA-xq4m-mc3c-vvg3 @anthropic-ai/claude-code (npm) Fixed in 1.0.93 Advisory →
Timeline
- 2026-10-02 Threatist record created from CVE-2025-66032
- 2026-10-03 Alias added: GHSA-xq4m-mc3c-vvg3
References
More anthropics Claude Code vulnerabilities
- TI-2025-36683 Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email CVSS 4.0HIGH 8.7
- TI-2025-37066 Claude Code's startup trust dialog could lead to Command Execution attack CVSS 4.0HIGH 8.7
- TI-2026-17554 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation CVSS 4.0MEDIUM 5.3
- TI-2025-40093 @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes CVSS 4.0HIGH 8.7
- TI-2025-36422 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution CVSS 4.0HIGH 8.7
- TI-2025-34550 Claude Code echo command allowed bypass of user approval prompt for command execution CVSS 4.0HIGH 8.7
Sources
- CVE-2025-66032 · CVE Program
- CVE-2025-66032 · NVD
- FIRST EPSS
- GHSA-xq4m-mc3c-vvg3 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences