Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool
CVE-2026-41686 · GHSA-p7fg-763f-g4gf · published 2026-04-29 · updated 2026-05-21
- Severity
- Medium
- CVSS score
- 4.8
- Chance of exploitation (EPSS)
- 0.12%
- Fixed in
- 0.91.1
- Exploitation No known exploitation
- Automatable No
- Technical impact Partial
- CISA SSVC
The BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes (0o666 for files, 0o777 for directories), leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read persisted agent state, and in containerized deployments could modify memory files to influence subsequent model behavior.
Upgrade @anthropic-ai/sdk to 0.91.1 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| @anthropic-ai/sdk | npm | >= 0.79.0, < 0.91.1 | 0.91.1 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
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.