Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
CRITICAL severity

GHSA-2vh9-42vm-xmv2 — lmdeploy

CRITICALFix: InternLM/lmdeploy@f05b4ad

GHSA-2vh9-42vm-xmv2 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 asCVE-2025-66455
Published
Sep 18, 2026
Updated
Sep 18, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 19, 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 GHSA-2vh9-42vm-xmv2.

EPSS Exploitation Probability

via FIRST.org ↗
0.7%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs52th percentile — riskier than 52% of all scored CVEsHighest risk

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

How urgent is this, really

GHSA-2vh9-42vm-xmv2 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.

Where this sits among everything scored

Of 377,166 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.

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

  1. A caller submits a DistServe P2P connection request containing a ZeroMQ address.
  2. The LMDeploy engine connects its ZeroMQ PULL socket to that address.
  3. handle_zmq_recv() receives messages using recv_pyobj().
  4. A malicious peer sends a crafted pickle object.
  5. 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
EcosystemPackageVulnerable rangeFix
🐍PyPIlmdeploy≥ 0.9.2&&< 0.16.00.16.0pip install --upgrade 'lmdeploy==0.16.0'

Detection & mitigation playbook

Open-source dependency

  1. 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.

  2. Fix

    Update lmdeploy to 0.16.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-2vh9-42vm-xmv2 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like GHSA-2vh9-42vm-xmv2 can be triaged on real exposure rather than presence alone.

Tailored to GHSA-2vh9-42vm-xmv2. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

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
O3 Security · Impact-Aware SCA

Is GHSA-2vh9-42vm-xmv2 in your dependencies?

O3 Security finds GHSA-2vh9-42vm-xmv2 across PyPI dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.

Scan my dependencies How O3 SCA works
GHSA-2vh9-42vm-xmv2: RCE (Critical 9.8) | O3 Security