CVE-2026-34452
Claude SDK for Python: Memory Tool Path Validation Race Condition Allows Sandbox Escape
No known exploitation. EPSS puts it in the 2nd percentile. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
What it is
From the CVE record
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.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
0.1% chance of exploitation activity in the next 30 days, which ranks it in the 2nd percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
7 events over 115 days, from the signal feeds we watch.
- Patch availablerecord updated
- Patch availablerecord updated
- Publishedweakness classified, att&ck mapped
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N
Scored 5.3 by NVD.
How it is reached
- Attack Vector LocalRequires local access to the vulnerable system (e.g. local login, malicious file)
- Attack Complexity HighRequires specific conditions like a race condition or non-default configuration
- Privileges Required LowRequires basic user-level privileges
- User Interaction NoneNo user interaction needed — fully automated exploitation
Scope
- Scope UnchangedImpact is limited to the vulnerable component itself
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity LowData modification is possible but limited in scope or consequence
- Availability NoneNo availability impact
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
- CollectionT1005Data from Local Systemmedium confidence
- DiscoveryT1083File and Directory Discoverymedium confidence
- Privilege EscalationT1068Exploitation for Privilege Escalationmedium confidence
Sources
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Claude Sdk For Python, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI