Vulnerability · Published Mar 31, 2026 · Assigned by GitHub_M
CVE-2026-34450Claude SDK for Python: Insecure Default File Permissions in Local Filesystem Memory Tool
Medium 4.8
In plain English
A medium-severity incorrect default permissions in anthropic-sdk-python from anthropics. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 2% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, 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. Both the synchronous and asynchronous memory tool implementations were affected. This issue has been patched in version 0.87.0.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | anthropic | 0.87.0 | GHSA-q5f5-3gjm-7mfm |
| PyPI | anthropic | 0.87.0 | PYSEC-2026-2114 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| anthropics | anthropic-sdk-python | >= 0.86.0, < 0.87.0 |
Weakness: CWE-276, CWE-732 · Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
References
- https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-q5f5-3gjm-7mfm x_refsource_CONFIRM
- https://github.com/anthropics/anthropic-sdk-python/commit/715030ceb4d6dd8d3546e999c680e29532bf1255 x_refsource_MISC
- https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0 x_refsource_MISC