How severe is CVE-2025-66455?

CVE-2025-66455 has a CVSS score of 9.8/10, rated CRITICAL. Immediate patching is strongly recommended.

Which packages are affected by CVE-2025-66455?

CVE-2025-66455 affects the following packages: lmdeploy (PyPI). Ecosystems affected: PyPI.

How do I fix CVE-2025-66455?

Update lmdeploy to 0.16.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-66455 is resolved across your whole dependency graph.

How do I detect CVE-2025-66455 in my PyPI dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for lmdeploy, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate CVE-2025-66455 if there is no patch (or I can't update yet)?

Do not deserialise data from untrusted sources: where the format allows it, restrict deserialisation to an explicit allowlist of expected types, and prefer a data-only format (JSON, Protobuf) over one that can reconstruct arbitrary objects until you can upgrade.

Is CVE-2025-66455 actively exploited in the wild?

No public exploit code has been indexed for CVE-2025-66455 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2025-66455?

CVE-2025-66455 has an EPSS (Exploit Prediction Scoring System) score of 1.3%, placing it in the 70th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is CVE-2025-66455?

CVE-2025-66455 is classified as Deserialization of Untrusted Data (CWE-502). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation. This is a high-impact weakness class that often enables remote code execution or data exposure.

When was CVE-2025-66455 published, and has it been updated?

CVE-2025-66455 was published on September 18, 2026 and was last updated on October 28, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍

🐍 PyPI

Not in CISA KEV

CRITICAL severity

CVE-2025-66455 — lmdeploy

CRITICALFix: InternLM/lmdeploy@f05b4ad

CVE-2025-66455 is a critical-severity (CVSS 9.8) Deserialization of Untrusted Data vulnerability in lmdeploy. A fix is available for lmdeploy — see the affected versions and patch details below.

LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py

Also known asGHSA-2vh9-42vm-xmv2PYSEC-2026-4077

Published

Sep 18, 2026

Updated

Oct 28, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Nov 4, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
A successful exploit gives an attacker total control of the affected component, not partial access.
CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2025-66455.

EPSS Exploitation Probability

via FIRST.org ↗

1.3%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs70th percentile — riskier than 70% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

Where this sits among everything scored

Real-World Exposure

1 pkg affected

🐍lmdeploy

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

Summary

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.

Affected components

HTTP entry point: lmdeploy/serve/openai/endpoints/distserve.py, POST /distserve/p2p_connect
Attacker-controlled peer address: DistServeConnectionRequest.remote_engine_endpoint_info.zmq_address
Vulnerable receiver: lmdeploy/pytorch/disagg/conn/engine_conn.py, EngineP2PConnection.handle_zmq_recv()
Unsafe operation: recv_pyobj(), which performs pickle deserialization

Vulnerable data flow

A caller submits a DistServe P2P connection request containing a ZeroMQ address.
The LMDeploy engine connects its ZeroMQ PULL socket to that address.
handle_zmq_recv() receives messages using recv_pyobj().
A malicious peer sends a crafted pickle object.
Python code executes during deserialization, before LMDeploy can perform any type or field validation.

A type check performed after recv_pyobj() cannot mitigate this issue because pickle payload execution occurs during deserialization.

Impact

Successful exploitation allows arbitrary code execution as the LMDeploy serving process. This can expose model weights, prompts, credentials, attached storage, cluster-network services, and host or GPU resources. An attacker may also modify or terminate the serving process.

Affected versions

Affected versions:

lmdeploy >= 0.9.2, < 0.16.0

The vulnerable P2P receiver was introduced in commit b0b705f7.

Remediation

The issue was fixed by replacing the pickle-based ZeroMQ protocol with JSON serialization:

send_pyobj() was replaced with send_json().
recv_pyobj() was replaced with recv_json().
Received objects are validated using the DistServeCacheFreeRequest Pydantic schema before use.
Invalid or off-schema messages are rejected without terminating the receive loop.

Fix commit:

https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2

The fix was released in LMDeploy 0.16.0.

Workarounds

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.
Block arbitrary outbound ZeroMQ connections from serving nodes.

These measures reduce exposure but do not make pickle deserialization safe. Upgrading to LMDeploy 0.16.0 or later is recommended.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`lmdeploy`	≥ 0.9.2&&< 0.16.0	0.16.0`pip install --upgrade 'lmdeploy==0.16.0'`

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for lmdeploy, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update lmdeploy to 0.16.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-66455 is resolved across your whole dependency graph.
Workarounds
Do not deserialise data from untrusted sources: where the format allows it, restrict deserialisation to an explicit allowlist of expected types, and prefer a data-only format (JSON, Protobuf) over one that can reconstruct arbitrary objects until you can upgrade.

Frequently Asked Questions

## Summary 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 authenticatio