Vulnerability · Published Mar 31, 2026 · Assigned by GitHub_M

CVE-2026-34452Claude SDK for Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape

Medium 5.8

In plain English

A medium-severity security flaw 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 4% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 4.0)5.8Medium
Exploit odds (30 days)0.1%top 96.3% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

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 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.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIanthropic0.87.0GHSA-w828-4qhx-vxx3
PyPIanthropic0.87.0PYSEC-2026-2115

Affected products (as reported)

VendorProductVersions
anthropics anthropic-sdk-python >= 0.86.0, < 0.87.0

Weakness: CWE-59, CWE-367 · Vector: CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N

References