npm package report

Is @anthropic-ai/claude-code safe?

28 known vulnerabilities, worst severity HIGH.

cvss
7.7

how bad it is if exploited, out of 10

epss
0.60%

chance of exploitation in the next 30 days

xyz score
3.4

CyberXYZ composite, out of 10

fig. 01 — GHSA-7835-87q9-rgvv, the advisory selected below

// advisories

GHSA-7835-87q9-rgvv

HIGHCVE-2026-55607

Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox

Affected
>= 2.1.38, < 2.1.163
Fixed in
2.1.163
Weakness
CWE-22
Published
2026-07-24
Source
github

GHSANVDMITREreferencereference

// dependencies

0 direct

Sign in for dependency paths and remediation

// ai model usage

Tracked for PyPI packages. HuggingFace models declare Python dependencies, so npm packages are not covered.

Checked 2026-09-22 at 03:44 UTC. The most recent advisory here was published 2026-07-24. Updated continuously from NVD, GHSA, OSV and CNA feeds.

Think a verdict here is wrong? Tell us — we respond within 2 business days.
Is @anthropic-ai/claude-code safe? npm package security report | CyberXYZ