GHSA-5474-4w2j-mq4c
Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories
Quick fix
GHSA-5474-4w2j-mq4c — @anthropic-ai/sdk: upgrade to the fixed version with the command below.
npm install @anthropic-ai/sdk@0.81.0Details
The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's name as a prefix, allowing reads and writes outside the sandboxed memory directory.
Users on the affected versions are advised to update to the latest version.
Claude SDK for TypeScript thanks [hackerone.com/nicksim](https://hackerone.com/nicksim) for reporting this issue!
Are you affected?
Enter the version of the package you're using.
Affected packages
References
- https://github.com/anthropics/anthropic-sdk-typescript/security/advisories/GHSA-5474-4w2j-mq4c[WEB]
- https://nvd.nist.gov/vuln/detail/CVE-2026-34451[ADVISORY]
- https://github.com/anthropics/anthropic-sdk-typescript/commit/0ac69b3438ee9c96b21a7d3c39c07b7cdb6995d9[WEB]
- https://github.com/anthropics/anthropic-sdk-typescript[PACKAGE]
- https://github.com/anthropics/anthropic-sdk-typescript/releases/tag/sdk-v0.81.0[WEB]