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.

Attack Vector Local

Attack Complexity Low

Privileges Required Low

Attack Requirements None

User Interaction None

Vulnerable System Confidentiality Impact Low

Vulnerable System Integrity Impact Low

Vulnerable System Availability Impact None

Subsequent System Confidentiality Impact None

Subsequent System Integrity Impact None

Subsequent System Availability Impact None

No CVSS v3.1

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

The EPSS score is 0.00012.

Exploitation none

Automatable no

Technical Impact partial

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions
anthropics anthropic-sdk-python affected
Version Status Constraints
>= 0.86.0, < 0.87.0 affected —

No data.

No data.

No data.

Project Subscriptions

No data.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-q5f5-3gjm-7mfm Claude SDK for Python has Insecure Default File Permissions in Local Filesystem Memory Tool
Fixes

Solution

No solution given by the vendor.

Workaround

No workaround given by the vendor.

References
Link Providers
https://github.com/anthropics/anthropic-sdk-python/commit/715030ceb4d6dd8d3546e999c680e29532bf1255 cve-icon cve-icon
https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0 cve-icon cve-icon
https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-q5f5-3gjm-7mfm cve-icon cve-icon
History

Wed, 01 Apr 2026 23:45:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Wed, 01 Apr 2026 02:15:00 +0000

Type Values Removed Values Added
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.
Title Claude SDK for Python: Insecure Default File Permissions in Local Filesystem Memory Tool
Weaknesses CWE-276
CWE-732
References
Metrics cvssV4_0

{'score': 4.8, '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'}

Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-04-01T13:35:18.879Z

Reserved: 2026-03-27T18:18:14.895Z

Link: CVE-2026-34450

cve-icon Vulnrichment

Updated: 2026-04-01T13:35:15.464Z

cve-icon NVD

Status : Undergoing Analysis

Published: 2026-03-31T22:16:19.987

Modified: 2026-04-01T14:23:37.727

Link: CVE-2026-34450

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses