{"cve":"CVE-2026-33625","nvd":{"published":"2026-09-18T18:17:06.640","modified":"2026-09-24T21:25:27.050","status":"Deferred","description":"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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","score":8.8},"cwes":["CWE-400"],"references":["https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3","https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr","https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr"],"products":[],"source":"nvd","synced_at":"2026-10-19T22:55:23.253742848+00:00"},"epss":{"cve":"CVE-2026-33625","score":0.00442,"percentile":0.38432,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-3hmm-rh5q-gwwr","url":"https://osv.dev/vulnerability/GHSA-3hmm-rh5q-gwwr","summary":"LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading","modified":"2026-10-01T17:56:11.912565414Z","packages":[{"ecosystem":"PyPI","name":"lmdeploy","purl":"pkg:pypi/lmdeploy","ranges":[">=0.12.1 <0.12.3"],"fixed":["0.12.3"]}]},{"id":"PYSEC-2026-4078","url":"https://osv.dev/vulnerability/PYSEC-2026-4078","summary":"LMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loading","modified":"2026-10-01T17:45:06.290194632Z","packages":[{"ecosystem":"PyPI","name":"lmdeploy","purl":"pkg:pypi/lmdeploy","ranges":[">=0.12.1 <0.12.3"],"fixed":["0.12.3"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}