# CVE-2025-66455: LMDeploy remote code execution via pickle deserialization in DistServe

Source: https://junglewise.ai/threats/cve-2025-66455-lmdeploy-remote-code-execution-via-pickle-deserialization-in  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-18. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2025-66455 · Severity: critical · CVSS 9.8 · Published 2026-09-18

LMDeploy is an inference serving framework that supports distributed deployments through its DistServe feature. An unauthenticated attacker with network access to the DistServe HTTP API can trigger the serving process to deserialize untrusted pickle objects from a remote ZeroMQ endpoint, leading to arbitrary code execution with the privileges of the serving process. This exposes model weights, credentials, and cluster resources.

Technologies: [lmdeploy (PyPI)](https://junglewise.ai/threats/technologies/lmdeploy). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2025-66455 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2025-66455 being exploited in the wild.

**How severe is CVE-2025-66455?** Critical severity, with a CVSS score of 9.8, published 18 September 2026.

**Which products and versions are affected?** lmdeploy (PyPI) >= 0.9.2, < 0.16.0, ECOSYSTEM:introduced=0.9.2,fixed=0.16.0.

**Is there a fix for CVE-2025-66455?** Yes. lmdeploy (PyPI): upgrade to 0.16.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2025-66455 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2025-66455?** Check whether you run lmdeploy (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- lmdeploy (PyPI): upgrade to 0.16.0 or later

  ```sh
  pip install "lmdeploy>=0.16.0"
  ```


## Technical details

LMDeploy's DistServe control plane uses PyZMQ's `recv_pyobj()` method to deserialize messages from ZeroMQ PULL sockets. The vulnerable code path is triggered via the `POST /distserve/p2p_connect` HTTP endpoint, which accepts an attacker-controlled ZeroMQ peer address in `DistServeConnectionRequest.remote_engine_endpoint_info.zmq_address`. When the LMDeploy engine connects to this address and calls `handle_zmq_recv()` in `engine_conn.py`, Python's pickle deserialization executes arbitrary code embedded in the crafted payload before any type validation occurs. API-key authentication is disabled by default, allowing unauthenticated exploitation. The vulnerability was fixed in LMDeploy 0.16.0 by replacing pickle-based serialization with JSON and adding Pydantic schema validation.

## Affected products

- InternLM LMDeploy 0.9.2 to 0.15.x

## Identifiers

- CVE-2025-66455
- GHSA-2vh9-42vm-xmv2
- PYSEC-2026-4077

## Timeline

- 2026-09-18: disclosed: GHSA-2vh9-42vm-xmv2 published
- 2026: patched: Fixed in LMDeploy 0.16.0 via commit f05b4ad8

## Related threats

- [LMDeploy arbitrary code execution via eval() of untrusted quant_dtype](https://junglewise.ai/threats/cve-2026-33625-lmdeploy-arbitrary-code-execution-via-eval-of-untrusted-quant)
- [LMDeploy SSRF bypass in URL validation](https://junglewise.ai/threats/lmdeploy-ssrf-bypass-in-url-validation-c4a40a8d)
- [LMdeploy remote code execution via pickle deserialization in zmq_rpc](https://junglewise.ai/threats/cve-2025-59953-lmdeploy-remote-code-execution-via-pickle-deserialization-in-zmq)
- [PYSEC-2026-1579 - InternLM LMDeploy code injection vulnerability](https://junglewise.ai/threats/cve-2025-3163-internlm-lmdeploy-code-injection-vulnerability)
- [PYSEC-2026-1577 - LMDeploy Improper Input Validation Vulnerability](https://junglewise.ai/threats/cve-2025-3162-lmdeploy-improper-input-validation-vulnerability)