CVE-2026-40068
High · 8.8CVSS
8.8
EPSS
0.6%
Published
May 5, 2026
CISA due date
—
The record
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.
Affected packages
| Ecosystem | Package | Introduced | Fixed |
|---|---|---|---|
| npm | @anthropic-ai/claude-code | 2.1.63 | 2.1.84 |
Related vulnerabilities
- GHSA-q5hj-mxqh-vv77 Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution Same vulnerability
- CVE-2026-54316 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code
- GHSA-fg94-h982-f3mm Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch Also affects @anthropic-ai/claude-code
- GHSA-vp62-r36r-9xqp Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside… Also affects @anthropic-ai/claude-code
- CVE-2026-39861 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code
- GHSA-5cwg-9f6j-9jvx Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege… Also affects @anthropic-ai/claude-code
- CVE-2026-35603 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code
- CVE-2026-33068 Claude Code is an agentic coding tool. Also affects @anthropic-ai/claude-code