CVE Intelligence
Critical Insecure deserialization

CVE-2025-59953 — LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmq_rpc.py) for supporting the RPC communications. In its core functionality call_and_response(), I found it will directly use the pickles.loads() to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server. Version 0.10.2 contains a patch.

Published Sep 16, 2026 · Updated Oct 14, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.8% (30-day exploitation probability)+8
  • Technical severity (critical)+10
  • CISA SSVC: exploitation "poc"+5
  • Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.8%
ahead of 56% of scored CVEs · Oct 14, 2026
Affects
Internlm
Lmdeploy
CVSS base
9.8
Critical · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
Yes
can an attacker script the kill-chain steps
Technical impact
Total
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Pip Lmdeploy: fixed in version 0.10.2 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Internlm Lmdeploy, Pip Lmdeploy).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. Apply the fixed version or the patch documented under Remediation.
  4. Search available logs for exploit probes matching the vulnerability class (insecure deserialization), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Internlm Lmdeploy version >= 0.9.1, < 0.10.2 Vulnerable CVE Program (cve.org) e CISA ADP
Pip Lmdeploy ≥ 0.9.1 and < 0.10.2 Vulnerable GitHub Security Advisories

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
9.8 CVSS 3.1 Critical 3.9 5.9 security-advisories@github.com via NIST National Vulnerability Database
9.8 CVSS 3.1 Critical — — GitHub, Inc. via GitHub Security Advisories
9.8 CVSS 3.1 Critical — — GitHub_M via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-502 · Deserialization of Untrusted Data

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Monitor serialized objects in requests and unexpected processes spawned by the runtime.
web/proxy/WAF logsnetwork IDS/IPSendpoint telemetry (EDR)application logs

Timeline

What happened to this CVE, newest first.

  • 2026
  • Fix documented
    Oct 14, 2026 · GitHub Security Advisories
  • Affected products added · pip/lmdeploy
    Oct 14, 2026 · GitHub Security Advisories
  • Affected products added · internlm/lmdeploy
    Oct 14, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 14, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 14, 2026
  • CVSS changed · 9.8
    Oct 14, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 14, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 14, 2026 · Alertas do Telegram
  • CVE published
    Sep 16, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 2× References added · Oct 14, 2026 – Oct 14, 2026
  • 1× Official description updated · Oct 14, 2026 – Oct 14, 2026

References

5 on the record

Elsewhere on this site

Internlm
every CVE for this vendor
Insecure deserialization
same class
CWE-502
other pages naming this weakness

Related CVEs (same products)

  • CVE-2025-66455 LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py 27d
  • CVE-2026-63764 LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass Jul 21, 2026
  • CVE-2026-46432 LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization Jun 9, 2026
  • CVE-2026-46517 LMDeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out Jun 9, 2026
  • CVE-2026-33626 LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading Apr 20, 2026
  • CVE-2025-67729 lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load() Dec 26, 2025

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2025-59953 is "LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy", rated Critical. It affects Lmdeploy (Internlm); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.8 describes technical severity. EPSS 0.80% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.