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.
Attack Parameters
Attack Vector
Local
Requires local access
Attack Complexity
High
Difficult to exploit
Attack Requirements
None
No additional conditions
Privileges Required
Low
Basic privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
Low
Partial data modification
Availability
None
No disruption
CVSS Vector v4.0
Weakness Type (CWE)
References 3
https://github.com/anthropics/anthropic-sdk-python/commit/6599043eee6e86dce1695…
security-advisories@github.com
https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0
security-advisories@github.com
https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-w82…
security-advisories@github.com