CVE-2026-34452

Published: Apr 01, 2026 Last Modified: Apr 01, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 5,8
Attack Vector: local
Attack Complexity: high
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 async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then returned the unresolved path for subsequent file operations. A local attacker able to write to the memory directory could retarget a symlink between validation and use, causing reads or writes to escape the sandbox. The synchronous memory tool implementation was not affected. This issue has been patched in version 0.87.0.

59

Improper Link Resolution Before File Access ('Link Following')

Draft
Common Consequences
Security Scopes Affected:
Confidentiality Integrity Access Control Other
Potential Impacts:
Read Files Or Directories Modify Files Or Directories Bypass Protection Mechanism Execute Unauthorized Code Or Commands
Applicable Platforms
Operating Systems: Windows, Unix
View CWE Details
367

Time-of-check Time-of-use (TOCTOU) Race Condition

Incomplete
Common Consequences
Security Scopes Affected:
Integrity Other Non-Repudiation
Potential Impacts:
Alter Execution Logic Unexpected State Modify Application Data Modify Files Or Directories Modify Memory Other Hide Activities
Applicable Platforms
All platforms may be affected
View CWE Details
https://github.com/anthropics/anthropic-sdk-python/commit/6599043eee6e86dce1695…
https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0
https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-w82…