Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories
CVE-2026-34451 · GHSA-5474-4w2j-mq4c · published 2026-04-01 · updated 2026-04-24
- Severity
- Medium
- CVSS score
- 5.4
- Chance of exploitation (EPSS)
- 0.37%
- Fixed in
- 0.81.0
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
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.
Upgrade @anthropic-ai/sdk to 0.81.0 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| @anthropic-ai/sdk | npm | >= 0.79.0, < 0.81.0 | 0.81.0 |
- CriticalMCP Path Traversal Allows Full-Filesystem Read and JWT Secret Exfiltration Leading to Account Takeoverlangflow, langflow-base
- Critical@zereight/mcp-gitlab: Unauthenticated arbitrary file read via `upload_markdown` enables PAT exfiltration and full account takeover@zereight/mcp-gitlab
- CriticalFlowise RCE via SQL Database Chain Nodeflowise, flowise-components
- CriticalLangroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file callslangroid
- Criticalfast-mcp-telegram: Bearer token path traversal bypasses reserved Telegram session protectionfast-mcp-telegram
- CriticalMCP Toolbox HTTP tool path parameters allow traversal to unintended endpointsgithub.com/googleapis/mcp-toolbox
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.