CVE-2026-34450
MEDIUM
4,8
Source: [email protected]
Attack Vector: local
Attack Complexity: low
Privileges Required: low
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
Description
AI Translation Available
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.
276
Incorrect Default Permissions
DraftCommon Consequences
Security Scopes Affected:
Confidentiality
Integrity
Potential Impacts:
Read Application Data
Modify Application Data
Applicable Platforms
Technologies:
ICS/OT, Not Technology-Specific
732
Incorrect Permission Assignment for Critical Resource
DraftCommon Consequences
Security Scopes Affected:
Confidentiality
Access Control
Integrity
Other
Potential Impacts:
Read Application Data
Read Files Or Directories
Gain Privileges Or Assume Identity
Modify Application Data
Other
Applicable Platforms
Technologies:
Cloud Computing, Not Technology-Specific
https://github.com/anthropics/anthropic-sdk-python/commit/715030ceb4d6dd8d3546e…
https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0
https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-q5f…