cve.bz

CVE-2026-105192 lmcache lmcache: Deserialization of Untrusted Data

9.8 criticalEPSS 1.0%Fix available

Critical (9.8) in lmcache lmcache. EPSS 1.0% estimated probability of exploitation activity in the next 30 days. Fixed in lmcache 0.5.6.

On this page
LMCache multiprocess mode, also called distributed mode, opens an unauthenticated ZeroMQ ROUTER so worker processes can register and share KV cache blocks. Messages on that socket are msgpack. Extension code 1 is passed to DeviceIPCWrapper.Deserialize, which calls pickle.loads, while the server is still decoding request arguments and before the handler runs. A single unauthenticated ZMQ DEALER message to the transport port (default 5555) therefore executes code as the user the LMCache process runs as. Official container images run that process as root. The transport binds to localhost unless the operator sets a routable address with --host, which is how multi-node deployments let peers connect. The decode path shipped in v0.3.9 and is present through v0.5.5, including the v0.5.6 release candidates. v0.5.6, published on 2026-10-14, removes pickle.loads from this path.

Severity

CVSS 3.1

9.8 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
1.0% (unchanged from 1.0% a week ago; 0.5% 30 days ago) estimated probability of exploitation activity in the next 30 days; 64th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: total, assessed 2026-10-07. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-306 Missing Authentication for Critical Functionality
CWE-502 Deserialization of Untrusted Data
OWASP Top 10
A07:2025 Authentication Failures, A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Fix and patched versions

  • lmcache (PyPI): fixed in 0.5.6

Ask an AI about this CVE

Show the promptExplain CVE-2026-105192 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-105192?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-105192?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-105192 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
LMCachefrom 0.3.9 before 0.5.6

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-w5f2-9q9c-ff4hPyPIlmcache>=0.3.9 <0.5.60.5.6

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

  • basesixtythree/B63-POC-CVE-2026-105192 Harbor Check: matches CVE 0 stars, Python, created
    CVE-2026-105192 (LMCache): pre-auth pickle deserialization RCE over the unauth ZMQ transport (single frame) — b63 showcase, lab-verified wi…
  • rxsklife/CVE-2026-105192 Harbor Check: matches CVE 0 stars, Python, created
    CVE-2026-105192 is a critical (CVSS 9.8) vulnerability in LMCache, an open-source distributed key-value cache for LLM inference engines lik…

Attack patterns (CAPEC)

  • CAPEC-586 Object Injection Likelihood: Medium · Severity: High
  • CAPEC-12 Choosing Message Identifier Likelihood: High · Severity: High
  • CAPEC-36 Using Unpublished Interfaces or Functionality Likelihood: Medium · Severity: High
  • CAPEC-62 Cross Site Request Forgery Likelihood: High · Severity: Very High
  • CAPEC-166 Force the System to Reset Values Severity: Medium
  • CAPEC-216 Communication Channel Manipulation

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON