Lmcache: Duplicate Advisory: Remote code execution via unsafe deserialization in multiprocess mode transport
Description
LMCache multiprocess mode (distributed mode) exposes an unauthenticated ZeroMQ ROUTER socket that accepts msgpack messages. A vulnerability in the deserialization process allows remote attackers to execute arbitrary code via a specially crafted message. This occurs because the server calls pickle.loads on untrusted data before request handling. The default transport binds to localhost, but if configured with a routable address, it can be exploited remotely. Official container images run the LMCache process as root, increasing the impact of exploitation.
CVSS v3.1
Score 9.8critical
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
LMCache multiprocess mode opens an unauthenticated ZeroMQ ROUTER socket for worker processes to share cache blocks. Messages are msgpack-encoded, and extension code 1 is passed to DeviceIPCWrapper.Deserialize, which uses pickle.loads to deserialize data. This unsafe deserialization occurs before request handling, allowing a single unauthenticated ZMQ DEALER message to execute arbitrary code as the LMCache process user. By default, the transport binds to localhost, but if the operator sets a routable address via the --host option, remote exploitation is possible. Official container images run the process as root, increasing the severity of this remote code execution vulnerability.
Potential Impact
Successful exploitation allows unauthenticated remote attackers to execute arbitrary code with the privileges of the LMCache process, which is root in official container images. This can lead to full system compromise, data loss, or service disruption. The vulnerability affects deployments where the transport is exposed to routable networks.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, operators should ensure the transport socket is bound only to localhost and not exposed to untrusted networks. Avoid setting the --host option to a routable address unless necessary and secure the environment accordingly.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-vv44-hjm2-qw2f
- Osv Schema Version
- 1.4.0
- Ecosystems
- ["PyPI"]
- Database Specific Severity
- CRITICAL
- Cvss Version
- 3.1
Threat ID: 6ad2aee82cdf04f656455156
Added to database: 10/16/2026, 23:10:32 UTC
Last enriched: 10/16/2026, 23:14:06 UTC
Last updated: 10/16/2026, 23:14:06 UTC
Views: 4
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.