CVE-2026-33625 json
LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading
published 2026-09-18 51 d ago modified 2026-10-01 38 d ago also EUVD-2026-83202 , GHSA-3hmm-rh5q-gwwr , PYSEC-2026-4078
- cvss
- 8.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 38%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- pypi lmdeploy 0.12.3
- internlm lmdeploy 0.12.3
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 47 d ago
Exploit prediction
0.44% chance of exploitation in the next 30 days, higher than 38% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | lmdeploy | >=0.12.1, <0.12.3 |
0.12.3 |
Affected products
- InternLM lmdeploy
Classification
- Weakness
-
- CWE-400 Uncontrolled Resource Consumption
References
-
github.com
/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr
exploit, web
-
github.com
/InternLM/lmdeploy/releases/tag/v0.12.3
web
-
github.com
/InternLM/lmdeploy
package
-
pypi.org
/project/lmdeploy
package
-
github.com
/advisories/GHSA-3hmm-rh5q-gwwr
advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-33625
advisory
Sources
- CVE List CVE-2026-33625
- GitHub Advisory GHSA-3hmm-rh5q-gwwr
- NVD CVE-2026-33625
- OSV PYSEC-2026-4078
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.