NVD / CVE Program· CNA GitHub_M

CVE-2025-66455: LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py

Noroxi assessment

Priority: Monitor (action score 39/100)

The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
Probability of exploitation in the next 30 days: 1.2% (FIRST EPSS); higher than 69.7% of all records.
Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
According to CISA the attack is automatable: targets can be found by mass scanning.
Fixed version: lmdeploy (PyPI) 0.16.0.

Low priority for now. Upgrade to lmdeploy (PyPI) 0.16.0 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.

CriticalCVSS 9.8 · v3.1—No exploit Fix available

Published: Sep 18, 2026
Updated: Oct 14, 2026
EPSS: 1.2% · 69th percentile
CWE: CWE-502

Report tools

JSON

Action score

Monitor

Low priority for now.

CVSS: 39 / 40 · 9.8 / 10
CISA KEV: 0 / 30 · Not listed
EPSS: 0 / 30 · 1.2%

CISA SSVC decision

Exploitation: none
Automatable: yes
Technical impact: total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: —
CNA · GitHub_M: 9.8; NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

Not in KEV: no record of exploitation in the wild
No public exploit code on record
A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Running WordPress? Scan your site free with WP Lens

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

—

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

InternLM lmdeploy
- >= 0.9.2, < 0.16.0affected

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

Ecosystem	Package	Affected range	Fix
PyPI	lmdeploy	from 0.9.2 · before 0.16.0	0.16.0

Same product

internlm: all records

Other highest-scoring records for the same primary product.

CVE-2026-33626LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
44Plan
CVE-2025-59953LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
39Monitor
CVE-2026-119706LMDeploy 0.9.0 through 0.18.0 Unauthenticated RCE via /update_weights Pickle Deserialization
37Monitor

Published before and after this one in the same product

← EarlierCVE-2026-92971Sep 17, 2026 · InternLM LMDeploy through 0.17.0 Assertion Denial of Service
34Monitor
← EarlierCVE-2026-92983Sep 17, 2026 · InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch
34Monitor
← EarlierCVE-2026-33625Sep 18, 2026 · LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
35Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / package	Fixed version	Source
PyPI:lmdeploy	0.16.0	Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

EPSS, last 120 days+1% in 7 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

InternLM/lmdeploycommit f05b4ad

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

CVE-2025-599532 days apartLMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
39Monitor
CVE-2026-7685030 days apartLMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector
37Monitor
CVE-2026-11970642 days apartLMDeploy 0.9.0 through 0.18.0 Unauthenticated RCE via /update_weights Pickle Deserialization
37Monitor
CVE-2025-67729266 days apartlmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()
35Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

Anyone who can reach it over the internet can trigger it.
No account or password is required.
No user action is required.
No special conditions are required; it is repeatable.

If successful

Confidentiality: high · data can be read
Integrity: high · data or configuration can be modified
Availability: high · the service can be disrupted

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

Weakness class (CWE)

CWE-502 · Deserialization of Untrusted Data

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

nvd-secondary

Root cause

Data received over the network is deserialized into the language’s native object format without verifying its source. Code paths inside the object can be triggered during deserialization.

The bug in code

The whole CWE-502 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

python

1payload = sock.recv(65536)
2job = pickle.loads(payload)

Fixed

python

1payload = sock.recv(65536)
2if not hmac.compare_digest(sign(payload), header_sig):
3    raise PermissionError("invalid signature")
4job = JobSchema.validate(json.loads(payload))