CVE-2026-34451
mediumPriorität · verfolgen · 22EPSS 0.003 · 28. PerzentilEUUSEPSS · bewertet 2026-10-27
Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.81.0, 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. This issue has been patched in version 0.81.0.
cvss
Technischer Schweregrad, 0–10. Eine Zeile je Quelle.
Basiswert 0–10 · höher = schwerwiegender · Vektor überfahren zum Auflösen⚠ Quellen uneinig · low–medium · 1.7–6.3
SSVC
Eine Handlungsentscheidung — aus Ausnutzung und Auswirkung.
schwächen
Die CWE-Schwächeklassen, zu denen dies gehört.
betroffene Produkte (3)
Betroffene Produkte und Versionsbereiche.
- anthropic claude sdk for typescript0.79.0 → 0.81.0nvdUScpe:2.3:a:anthropic:claude_sdk_for_typescript:*:*:*:*:*:*:*:*
Advisories (1)
Hersteller- und Ökosystem-Meldungen dazu.
- GHSA-5474-4w2j-mq4cClaude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories2026-04-01ghsa · osvUS
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!
auch bekannt als (3)
Weitere Namen und Kennungen dieser Entität.
quellen
Welche Quellen diesen Datensatz belegen und wann.
Referenzen (11)
Externe Belege — Patches, Meldungen, Analysen.
- https://access.redhat.com/security/cve/cve-2026-34451cnnvd
- https://github.com/anthropics/anthropic-sdk-typescript/commit/0ac69b3438ee9c96b21a7d3c39c07b7cdb6995d9cnnvd
- https://github.com/anthropics/anthropic-sdk-typescript/releasesPatchcnnvd
- https://github.com/anthropics/anthropic-sdk-typescript/releases/tag/sdk-v0.81.0cnnvd
- https://github.com/anthropics/anthropic-sdk-typescript/security/advisories/GHSA-5474-4w2j-mq4ccnnvd
- https://github.com/anthropics/anthropic-sdk-typescript/commit/0ac69b3438ee9c96b21a7d3c39c07b7cdb6995d9enisa_euvd
- https://github.com/anthropics/anthropic-sdk-typescript/releases/tag/sdk-v0.81.0enisa_euvd
- https://github.com/anthropics/anthropic-sdk-typescript/security/advisories/GHSA-5474-4w2j-mq4cenisa_euvd
Angreifer nutzen Schwachstellen wie diese gegen im Internet exponierte Dienste aus. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan