LMDeploy Vulnerabilities

pip LLM Inference

AI Threat Alert tracks 10 known vulnerabilities in LMDeploy, 3 rated critical — an AI/ML llm inference in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

Data sources
10
Total CVEs
3
Critical
pip
Ecosystem
Sep 18, 2026
Last CVE
60%
Patch Rate
17d
Avg Time to Patch
8,082 stars 752 forks 597 issues 1 dependents Last push Sep 18, 2026
View on GitHub

Known Vulnerabilities (8 total, page 1 of 1)

Severity CVE ID Summary CVSS Published
HIGH GHSA-39wr-7q6h-cf68 LMDeploy has an SSRF bypass 7.5 Sep 18, 2026 CRITICAL CVE-2025-66455 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/p2 9.8 Sep 18, 2026 HIGH CVE-2026-33625 LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in `lmdeploy/pytorch/config.py` line 620 that allows an attacker to execute arbitrary Python code by publishing a malicious HuggingFace model with a crafted `quantization_config.quant_dtype` value. When a user loads the model with lmdeploy, the `quant_dtype` is passed to `eval(f'torch.{quant_dtype}')` without any validation. Version 0.12.3 cont 8.8 Sep 18, 2026 CRITICAL CVE-2025-59953 LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy 9.8 Sep 16, 2026 CRITICAL CVE-2026-76850 LMDeploy: RCE via unauth pickle deserialization 9.8 Aug 19, 2026 HIGH CVE-2026-63764 lmdeploy: SSRF via redirect bypasses private IP guard 8.6 Jul 21, 2026 HIGH CVE-2026-46517 LMDeploy: hardcoded trust_remote_code enables RCE 7.8 May 21, 2026 HIGH CVE-2025-67729 lmdeploy: Deserialization enables RCE 8.8 Dec 26, 2025

Frequently asked questions

What is LMDeploy?

LMDeploy is an AI/ML llm inference tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does LMDeploy have?

LMDeploy has 10 known CVEs, 3 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is LMDeploy distributed in?

LMDeploy is distributed via the pip ecosystem and categorized as llm inference.

Where does the LMDeploy vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of LMDeploy?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor LMDeploy in your stack

Get instant alerts when new vulnerabilities affect LMDeploy. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring