Vulnerability  ·  2026-09-19

LMDeploy — code injection via malicious HuggingFace model repo at load time

VulnerabilityHigh impactGlobalCVE-2026-33625
LMDeploy, InternLM's toolkit for compressing, deploying, and serving LLMs, contained a code-injection vulnerability triggered simply by loading a specially crafted HuggingFace model repository, giving the model publisher arbitrary code execution on the serving host.
This is a classic AI supply-chain attack vector: any team that pulls community models from HuggingFace and serves them via LMDeploy is one malicious model download away from full host compromise, and the pattern recurs across LMDeploy releases (echoing earlier CVE-2025-3163 / CVE-2026-46432 trust_remote_code issues).
A code injection flaw in lmdeploy/pytorch/config.py allows an attacker who publishes a malicious HuggingFace model to execute arbitrary Python code on the machine of any operator who loads that model via LMDeploy — a recurrence of the trust_remote_code-style pattern that has affected LMDeploy previously.
LMDeploy 0.12.1 through 0.12.2
Upgrade to LMDeploy 0.12.3 or later.
LMDeploy release notes (fix)NVD CVE-2026-33625
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →