{"id":"CVE-2026-33625","title":"LMDeploy is a toolkit for compressing, deploying, and serving large language models","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 arbitra…","severity":"high","cvss":8.8,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","cwe":["CWE-400"],"vendor":"InternLM","product":"lmdeploy","affected":["lmdeploy >= 0.12.1, < 0.12.3"],"patched":["lmdeploy 0.12.3"],"published":"2026-09-18","updated":"2026-09-22","sourceUpdated":"2026-09-22T16:17:47.620","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-33625","references":[{"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3","label":"security-advisories@github.com"},{"url":"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr","label":"security-advisories@github.com"},{"url":"https://github.com/InternLM/lmdeploy/security/advisories/GHSA-3hmm-rh5q-gwwr","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"},{"url":"https://github.com/advisories/GHSA-3hmm-rh5q-gwwr"},{"url":"https://github.com/InternLM/lmdeploy"}],"tags":["nvd","cve.org","ghsa","pip","osv","exploit-available"],"epss":0.00242,"epssPercentile":0.15633,"aliases":["GHSA-3hmm-rh5q-gwwr"],"ecosystem":"pip","exploitAvailable":true,"ssvc":{"exploitation":"poc","automatable":"no","technicalImpact":"total","timestamp":"2026-09-22T15:07:33.233899Z"},"ingestedAt":"2026-09-18T17:46:41.531Z","slug":"CVE-2026-33625","body":"## Overview\n\nLMDeploy 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2026-33625)\n\nAffected packages:\n\n- `lmdeploy >= 0.12.1, < 0.12.3`\n\nPatched in:\n\n- `lmdeploy 0.12.3`\n\nSource: https://github.com/advisories/GHSA-3hmm-rh5q-gwwr","depth":"midnight","depthScore":60,"depthScoreParts":{"impact":48.4,"likelihood":0,"exploitation":12,"ransomware":0},"changes":[{"seq":209172,"id":"CVE-2026-33625","ts":1790093218678,"field":"exploit_available","old":"false","new":"true"}]}