# CVE-2026-40068: @anthropic-ai/claude — Fixed in 2.1.84

📦 npm

Not in CISA KEV

# CVE-2026-40068 — @anthropic-ai/claude-code

CVE-2026-40068 is a Improper Input Validation vulnerability in @anthropic-ai/claude-code. A fix is available for @anthropic-ai/claude-code — see the affected versions and patch details below.

Claude Code arbitrary code execution via git worktree commondir trust dialog bypass

Also known as[GHSA-q5hj-mxqh-vv77](/vulnerability/GHSA-q5hj-mxqh-vv77)

Published

May 5, 2026

Updated

Oct 28, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Nov 8, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

## Exploitation Status

### No confirmed exploitation observed yet

-   A successful exploit gives an attacker total control of the affected component, not partial access.
-   CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-40068.

## EPSS Exploitation Probability

[via FIRST.org ↗](https://www.first.org/epss/)

0.3%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs24th percentile — riskier than 24% of all scored CVEsHighest risk

0.00%0.35%0.71%1.06%0.1%0.3%Jun 26Sep 26Nov 26

Probability of exploitation in the next 30 days, from [FIRST.org EPSS](https://www.first.org/epss/).

## Real-World Exposure

1 pkg affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, and reverse-dependency count shows how many other packages break if it stays unpatched.

281other npm packages depend on this — each one inherits the vulnerability until it's patched upstream

`@anthropic-ai/claude-code`npm

14.1Mdownloads / week

## Description

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](https://hackerone.com/masato_anzai) for reporting this issue.

## Affected Packages

1 total 1 fixed

Ecosystem

Package

Vulnerable range

Fix

📦npm

`@anthropic-ai/claude-code` 

≥ 2.1.63&&< 2.1.84

2.1.84`npm install @anthropic-ai/claude-code@2.1.84`

## Affected Products

1 product · 1 configurations

Application

`claude code`anthropic

≥ 2.1.63 && < 2.1.84

range

## Detection & mitigation playbook

Open-source dependency

1.  ### Detect
    
    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
    
2.  ### Fix
    
    Update @anthropic-ai/claude-code to 2.1.84 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-40068 is resolved across your whole dependency graph.
    
3.  ### Workarounds
    
    Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.
    

## Frequently Asked Questions

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 perfor

O3 Security · Impact-Aware SCA

### Is CVE-2026-40068 in your dependencies?

Find it across npm, including transitive dependencies.

[Scan my dependencies](/book-demo) [How O3 SCA works](/impact-aware-sca)