Claude Code arbitrary code execution via git worktree commondir trust dialog bypass
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Passive
- Attack complexity
- Low
- Attack requirements
- Present
- 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
In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted, causing Claude Code to bypass its trust confirmation dialog and immediately execute hooks defined in `.claude/settings.json`. Exploitation requires the victim to clone the malicious repository and run Claude Code within it, and the attacker must know or guess a path the victim had already trusted. This issue has been fixed in version 2.1.84.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- 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 | 2.1.63 to before 2.1.84 | 2.1.84 | Patch available | CNA |
| — | @anthropic-ai/claude-code (npm) | 2.1.63 to before 2.1.84 | 2.1.84 | Patch available | GHSA-q5hj-mxqh-vv77 |
- claude-code Vendoranthropics Affected 2.1.63 to before 2.1.84 Fixed in 2.1.84 Patch available CNA
- @anthropic-ai/claude-code (npm) Vendor— Affected 2.1.63 to before 2.1.84 Fixed in 2.1.84 Patch available GHSA-q5hj-mxqh-vv77
CPE configurations NVD · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* | 2.1.63 to before 2.1.84 | Vulnerable | anthropics |
- cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* Versions 2.1.63 to before 2.1.84 Vulnerable ·anthropics
Remediation
- Fix · CNA claude-code (anthropics) Fixed in 2.1.84
- Fix · GHSA-q5hj-mxqh-vv77 @anthropic-ai/claude-code (npm) Fixed in 2.1.84 Advisory →
Timeline
- 2026-10-02 Threatist record created from CVE-2026-40068
- 2026-10-03 Alias added: GHSA-q5hj-mxqh-vv77
References
More anthropics Claude Code vulnerabilities
- TI-2025-40558 Claude Code Command Validation Bypass Allows Arbitrary Code Execution CVSS 4.0HIGH 8.7
- 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
Sources
- CVE-2026-40068 · CVE Program
- CVE-2026-40068 · NVD
- FIRST EPSS
- GHSA-q5hj-mxqh-vv77 · 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