CVE-2025-59953: LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
• EPSS 0.8%, percentile 56: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 56% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes lmdeploy (PyPI) >= 0.9.1, < 0.10.2, fixed in 0.10.2. Check your lockfile, including transitive dependencies.

What it is

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmqrpc.py) for supporting the RPC communications. In its core functionality callandresponse(), I found it will directly use the pickles.loads() to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server. Version 0.10.2 contains a patch.

From the GitHub advisory

Description

The LMdeploy implements an rpc server (AsyncRPCServer in zmqrpc.py) for supporting the RPC communications. In its core functionality callandresponse(), I found it will directly use the pickles.loads() to deserialize the received messages without any sanitization, hence resulting in a remote code execution vulnerability by this RPC server.

Proof of Concept

Step1: The victim user starts a RPC server that connects to its network interface. We give our example code (server.py) in the attachment, you can reproduce directly with server.py.

Step2: The attacker can then send malicious pickle dump data to the remote RPC address for the attack. We give a example to show how can an attacker acquire a command shell:

Weakness type: CWE-502.

Product: lmdeploy (PyPI) · Assigned by: GitHub_M · Published: 2026-09-16

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Privileges required: none (no login)
• User interaction: none
• Scope: unchanged

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 0.80% probability of exploitation activity in the next 30 days; percentile 56.

Timeline

• 2026-09-16 — CVE record published by GitHub_M
• 2026-09-16 — GitHub-reviewed advisory GHSA-5h8j-6crg-7rmw published (critical)
• 2026-09-18 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-5h8j-6crg-7rmw github.com
2. CVE.org record CVE-2025-59953 cve.org
3. NVD entry CVE-2025-59953 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com

Critical PyPI advisories · Today’s Security Digest