9.8
CRITICAL CVSS 3.1
CVE-2026-76850
LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector
Description

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.

INFO

Published Date :

Aug. 19, 2026, 10:17 p.m.

Last Modified :

Aug. 19, 2026, 10:17 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-76850 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Internlm lmdeploy
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 CRITICAL 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 3.1 CRITICAL [email protected]
CVSS 3.1 CRITICAL MITRE-CVE
CVSS 4.0 CRITICAL 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 4.0 CRITICAL [email protected]
Solution
Secure the deserialization of peer messages and enforce authentication for API endpoints.
  • Validate peer message integrity before deserialization.
  • Enforce authentication for API endpoints.
  • Restrict access to PULL socket endpoints.
  • Update LMDeploy to the latest secure version.
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-76850 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-76850 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-76850 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-76850 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Aug. 19, 2026

    Action Type Old Value New Value
    Added Affected [{'repo': 'https://github.com/InternLM/lmdeploy', 'vendor': 'InternLM', 'product': 'lmdeploy', 'versions': [{'status': 'affected', 'version': '0.9.2', 'lessThan': '0.16.0', 'versionType': 'semver'}], 'packageURL': 'pkg:pypi/lmdeploy', 'packageName': 'lmdeploy', 'collectionURL': 'https://pypi.org', 'defaultStatus': 'unaffected'}]
    Added Description LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.
    Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
    Added CWE CWE-502
    Added Reference https://github.com/InternLM/lmdeploy
    Added Reference https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L61
    Added Reference https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L79
    Added Reference https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2
    Added Reference https://github.com/InternLM/lmdeploy/issues/4804
    Added Reference https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0
    Added Reference https://www.vulncheck.com/advisories/lmdeploy-remote-code-execution-via-unsafe-pickle-deserialization-in-the-disaggregated-serving-peer-connector
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.