VULNpocalypse

CVE-2026-105192: LMCache Unauthenticated RCE in multiprocess mode via pickle deserialization

Advisory generated from the CVE record, CISA, Exploit Observer and VEDAS: what it is, whether it is exploited, who is affected, and how to fix and detect it.

Generated by VEDAS. Scores as of 2026-11-01 19:19 UTC. Rebuilt every few hours from cve-scores, CISA KEV and vedas-signatures. How this works and its limits.

What it is

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.

Description quoted from the CVE record (assigned by JFROG, published 2026-10-07).

Weakness: CWE-502: Deserialization of Untrusted Data; CWE-306: Missing Authentication for Critical Function

How it can be exploited

Exploitable over the network with low attack complexity needing no privileges and no user interaction. Impact: confidentiality high, integrity high, availability high. CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CISA assessment (SSVC): CISA has no evidence of exploitation. Automatable: yes. Technical impact: total.

Public exploit evidence (Exploit Observer)

Also known as: EUVD-2026-94261, GHSA-vv44-hjm2-qw2f, GHSA-w5f2-9q9c-ff4h

VEDAS cluster: VEDAS:DOOMSABLE

Exploit Observer links 4 pieces of public exploit code or detection modules that name this CVE or one of its aliases.

Exploit code and modules (4)

Code that names this CVE. A repository can be a working exploit, a scanner, a fake or malware; read it before running anything.

Research and write-ups (3)

Vulnerability databases and vendor advisories (6)

Catalogue entries, not exploit evidence.

News (1)

5 more references returned by Exploit Observer did not name this CVE or an alias, so they are left out.

VEDAS data as of 2026-11-01T17:12 UTC; fetched 2026-11-02.

Live scores

EPSS
0.010
some chance of attack soon
VEDAS
0.977
strong exploit evidence
On CISA KEV
Not listed
Detection rule
Suricata

Who is affected

ProductAffectedNot affected
LMCache LMCache (lmcache)from 0.3.9 before 0.5.6Not stated

Version ranges exactly as the CVE record states them. “Before X” means X is the first fixed version.

Exploit Observer also maps it to: pypi lmcache.

How to fix it

Fixed versions stated in the CVE record: 0.5.6.

Vendor guidance:

How to detect it

Suricata rules (network detection)

1 rule that alert on traffic matching this exploit: VEDAS CVE-2026-105192 LMCache - Unauthenticated ZeroMQ msgpack pickle deserialization RCE attempt. Add them to your Suricata rule set and reload.

Show the rules
suricata
alert tcp $EXTERNAL_NET any -> $HOME_NET 5555 (msg:"VEDAS CVE-2026-105192 LMCache - Unauthenticated ZeroMQ msgpack pickle deserialization RCE attempt"; flow:established,to_server; dsize:>30; content:"|80|"; fast_pattern; pcre:"/(?:c(?:os|nt|posix)\x0asystem\x0a|csubprocess\x0a(?:Popen|run|call|check_output)|c(?:__builtin__|builtins)\x0a(?:eval|exec|__import__)|\x8c[\x02-\x0c](?:os|nt|posix|subprocess|builtins|platform|pty)\x8c[\x02-\x14][A-Za-z_]+\x93)/"; classtype:attempted-admin; reference:cve,CVE-2026-105192; reference:url,https://www.exploit.observer/?keyword=CVE-2026-105192&match=exact; reference:url,https://subdomain.center/?engine=ammonites&keyword=lmcache&match=exact; sid:1090003; rev:1;)

CVE-2026-105192.rules on GitHub

References

Vendor advisories and patches

Exploits and technical analysis

Other references

Other databases

Where this comes from

This advisory is generated automatically by VEDAS from: CVE.org record, cve-scores (EPSS and VEDAS), Exploit Observer, vedas-signatures. Text in quotes is reproduced from the source; everything else is a fixed template filled with source fields. Nothing here is written by a language model. Check the vendor advisory before acting, and read how VEDAS and Exploit Observer work, and their limits.