npm package report

Is @anthropic-ai/sdk safe?

@anthropic-ai/sdk (npm) has 2 known vulnerabilities, the worst rated MODERATE. Upgrade to 0.91.1 or later to clear all of them. No malicious-package signal is recorded.

// reach

3 direct dependencies

none carry a known advisory

137 packages depend on it

an advisory here reaches each of them

Create a free accountfor every dependency path, dependent and what to upgrade

// ai model usage

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

cvss

4.8

medium

CVSS v4.0 base score out of 10

epss

0.12%

low

chance of exploitation in 30 days, 2nd percentile of all CVEs

xyz score

not scored

CyberXYZ composite out of 10

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

// 2 advisories

GHSA-p7fg-763f-g4gf

MODERATEGitHub ratingCVE-2026-41686

The BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes (0o666 for files, 0o777…

Full advisory text at GitHub advisory or NVD.

// cvss v4.0 vector

CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N

Attack vector: Local
Attack complexity: Low
Attack requirements: None
Privileges required: Low
User interaction: None
Confidentiality (vulnerable system): Low
Integrity (vulnerable system): Low
Availability (vulnerable system): None
Confidentiality (subsequent systems): None
Integrity (subsequent systems): None
Availability (subsequent systems): None

// questions

Is @anthropic-ai/sdk safe to install?

CyberXYZ does not call a package safe in absolute terms. It records 2 known vulnerabilities for @anthropic-ai/sdk (npm), the worst rated MODERATE, and no malicious-package signal. Whether it is acceptable depends on the version you run.

Does @anthropic-ai/sdk have known vulnerabilities?

Yes. CyberXYZ records 2 known vulnerabilities for @anthropic-ai/sdk (npm), the worst rated MODERATE. They are GHSA-p7fg-763f-g4gf, GHSA-5474-4w2j-mq4c.

Which version of @anthropic-ai/sdk should I use?

0.91.1 or later clears every advisory recorded for @anthropic-ai/sdk (npm). Check the release you pick before installing it.

How do I check @anthropic-ai/sdk before installing?

Search @anthropic-ai/sdk in CyberXYZ Check at https://cyberxyz.io/check?q=%40anthropic-ai%2Fsdk. The xyz Scanner checks a project's dependencies, and CyberXYZ Proxy checks each package as it is installed.

Checked 2026-11-14 at 07:04 UTC. The most recent advisory here was published 2026-04-29. Updated continuously from NVD, GHSA, OSV and CNA feeds.