# @anthropic-ai/sdk (npm) vulnerabilities

2 known vulnerabilities (2 medium), with the versions each affects and the releases that fix them.

## At a glance

- Latest release: not known (cve.now hasn't read this package's releases)
- Newest unaffected release: not known without release data
- Registry: https://www.npmjs.com/package/@anthropic-ai/sdk

## Advisories (2)

### [CVE-2026-41686](https://cve.now/CVE-2026-41686): Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool

- Severity: Medium 4.8
- Published: May 4, 2026
- Affected: from 0.79.0, fixed in 0.91.1.

### [CVE-2026-34451](https://cve.now/CVE-2026-34451): Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories

- Severity: Medium 6.3
- Published: Mar 31, 2026
- Affected: from 0.79.0, fixed in 0.81.0.

---

Source: cve.now
Built by [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.
Page: https://cve.now/packages/npm/@anthropic-ai/sdk
Site guide for agents: https://cve.now/llms.txt
Uses NVD data; not endorsed by NVD.