vLLM affected by RCE via auto_map dynamic module loading during model initialization

SummaryvLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup.--- ImpactAn attacker who can influence the model repo/path local directory or remote Huggin...

MAL-2026-6538 Malicious code in db-plog (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 961a6a108104105727b81399e6a3a6d56636cb79ae8fbfbbc33528f90d890d99 On every Model instantiation — the package's documented primary API — dist/index.js executes execSync'npm install db-connector-log --no-warnings...

Arbitrary Code Injection

Overview Affected versions of this package are vulnerable to Arbitrary Code Injection via the model initialization process when trustremotecode=True is hardcoded in multiple HuggingFace model-loading call sites. An attacker can execute arbitrary code by supplying a malicious model repository...

CVE-2026-46432

CVE-2026-46432 (LMDeploy) affects lmdeploy

EUVD-2026-34084

A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The issue arises because the trustremotecode parameter, intended to prevent remote code execution, is...

CVE-2026-5241: Inclusion of Functionality from Untrusted Control Sphere

A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The issue arises because the trustremotecode parameter, intended to prevent remote code execution, is...

GHSA-2PC9-4J83-QJMR vLLM affected by RCE via auto_map dynamic module loading during model initialization

Summary vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup. --- Impact An attacker who can influence the model repo/path local directory or remote...

Arbitrary Code Injection

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Arbitrary Code Injection via the automap process during model initialization, even when trustremotecode is false. An attacker can execute arbitrary...

vLLM affected by RCE via auto_map dynamic module loading during model initialization

Summary vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup. --- Impact An attacker who can influence the model repo/path local directory or remote...