Browse / MCP and Tool Server Flaws / CVE-2026-40068
Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution
- Class
- MCP and Tool Server Flaws (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- @anthropic-ai/claude-code (npm)
- Gets past
- Approval or confirmation prompt
- CVSS
- CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- EPSS
- 0.3% chance of exploitation in 30 days
How it works, in short
A crafted repository's worktree commondir file points to an already trusted path, so the trust dialog is skipped and repo-defined hooks run immediately. (Our summary, written by a model. The source text is below.)
Details
Claude Code used the git worktree commondir file when determining folder trust but did not validate its contents. By crafting a repository with a commondir file pointing to a path the victim had previously trusted, an attacker could bypass the trust dialog and immediately execute malicious hooks defined in .claude/settings.json. Exploiting this required the victim to clone a malicious repository and run Claude Code within it, and for the attacker to know or guess a path the victim had already trusted.
Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.
Claude Code thanks hackerone.com/masato_anzai for reporting this issue.
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-q5hj-mxqh-vv77
- https://nvd.nist.gov/vuln/detail/CVE-2026-40068
- https://github.com/anthropics/claude-code
Source: GitHub Advisory Database, used under CC BY 4.0.