npm package report

Is @anthropic-ai/sdk safe?

2 known vulnerabilities, worst severity MODERATE.

cvss
4.8

how bad it is if exploited, out of 10

epss
0.10%

chance of exploitation in the next 30 days

xyz score
not scored

CyberXYZ composite, out of 10

fig. 01 — GHSA-p7fg-763f-g4gf, the advisory selected below

// advisories

GHSA-p7fg-763f-g4gf

MODERATECVE-2026-41686

The BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes (0o666 for files, 0o777 for directories), leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read persisted agent state, an

Affected
>= 0.79.0, < 0.91.1
Fixed in
0.91.1
Weakness
CWE-732
Published
2026-04-29
Source
github

GHSANVDMITREreference

// 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 00:54 UTC. The most recent advisory here was published 2026-04-29. 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/sdk safe? npm package security report | CyberXYZ