cve.bz

CVE-2025-66455 internlm lmdeploy: Deserialization of Untrusted Data

9.8 criticalEPSS 1.3%Fix available

Critical (9.8) in internlm lmdeploy. EPSS 1.3% estimated probability of exploitation activity in the next 30 days. Fixed in lmdeploy 0.16.0.

On this page
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.

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
1.3% (unchanged from 1.3% a week ago; 0.7% 30 days ago) estimated probability of exploitation activity in the next 30 days; 70th 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 2026-09-18. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-502 Deserialization of Untrusted Data
OWASP Top 10
A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Awaiting analysis
Record from
the NVD, synced

Fix and patched versions

  • lmdeploy (PyPI): fixed in 0.16.0

Ask an AI about this CVE

Show the promptExplain CVE-2025-66455 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2025-66455?via=ask-ai-copy and https://cve.bz/cve/CVE-2025-66455?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-2025-66455 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
InternLM lmdeploy>= 0.9.2, < 0.16.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-2vh9-42vm-xmv2PyPIlmdeploy>=0.9.2 <0.16.00.16.0
PYSEC-2026-4077PyPIlmdeploy>=0.9.2 <0.16.00.16.0

Attack patterns (CAPEC)

  • CAPEC-586 Object Injection Likelihood: Medium · Severity: High

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

References

Check your stackJSON