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...
Full CISO analysis pending enrichment.
What systems are affected?
| Package | Ecosystem | Vulnerable Range | Patched |
|---|---|---|---|
| LMDeploy | pip | >= 0.12.1, < 0.12.3 | 0.12.3 |
Do you use LMDeploy? You're affected.
How severe is it?
What is the attack surface?
What should I do?
Patch available
Update LMDeploy to version 0.12.3
Which compliance frameworks are affected?
Compliance analysis pending. Sign in for full compliance mapping when available.
Frequently Asked Questions
What is 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 contains a patch.
Is CVE-2026-33625 actively exploited?
No confirmed active exploitation of CVE-2026-33625 has been reported, but organizations should still patch proactively.
How to fix CVE-2026-33625?
Update to patched version: LMDeploy 0.12.3.
What is the CVSS score for CVE-2026-33625?
CVE-2026-33625 has a CVSS v3.1 base score of 8.8 (HIGH).
What are the technical details?
Original Advisory
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 contains a patch.
Weaknesses (CWE)
CWE-400 Uncontrolled Resource Consumption
Primary
CWE-400 Uncontrolled Resource Consumption
Primary
CWE-400 Uncontrolled Resource Consumption CWE-400 — Uncontrolled Resource Consumption: The product does not properly control the allocation and maintenance of a limited resource.
- [Architecture and Design] Design throttling mechanisms into the system architecture. The best protection is to limit the amount of resources that an unauthorized user can cause to be expended. A strong authentication and access control model will help prevent such attacks from occurring in the first place. The login application should be protected against DoS attacks as much as possible. Limiting the database access, perhaps by caching result sets, can help minimize the resources expended. To further limit the potential for a DoS attack, consider tracking the rate of requests received from users and blocking requests that exceed a defined rate threshold.
- [Architecture and Design] Mitigation of resource exhaustion attacks requires that the target system either: The first of these solutions is an issue in itself though, since it may allow attackers to prevent the use of the system by a particular valid user. If the attacker impersonates the valid user, they may be able to prevent the user from accessing the server in question. The second solution is simply difficult to effectively institute -- and even when properly done, it does not provide a full solution. It simply makes the attack require more resources on the part of the attacker. recognizes the attack and denies that user further access for a given amount of time, or uniformly throttles all requests in order to make it more difficult to consume resources more quickly than they can again be freed.
Source: MITRE CWE corpus.
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H References
Timeline
Related Vulnerabilities
CVE-2026-76850 9.8 LMDeploy: RCE via unauth pickle deserialization
Same package: lmdeploy CVE-2025-59953 9.8 Analysis pending
Same package: lmdeploy CVE-2025-66455 9.8 Analysis pending
Same package: lmdeploy CVE-2025-67729 8.8 lmdeploy: Deserialization enables RCE
Same package: lmdeploy CVE-2026-63764 8.6 lmdeploy: SSRF via redirect bypasses private IP guard
Same package: lmdeploy