CVE-2026-105753

A flaw was found in vLLM. This vulnerability allows a remote user to cause a Denial of Service DoS on the model serving engine. The issue occurs when a multimodal request is rejected after media processing, causing the frontend and backend caches to become desynchronized. A subsequent request...

CVE-2026-13717

CVE-2026-13717 describes a misconfiguration in the Red Hat OpenShift AI (RHOAI) MaaS Gateway used in a model-serving context. The flaw permits a standard user with low privileges to intercept, read, log, and alter MaaS model traffic, including sensitive data such as access keys, input prompts, an...

CVE-2026-13717

A flaw was found in the Red Hat OpenShift AI RHOAI MaaS Gateway. Improper configuration of the Gateway in a model-serving context allows a standard user with low privileges to intercept, read, log, and alter all MaaS model traffic. This includes sensitive information such as access keys, input...

CVE-2026-13717: Improper Access Control

A flaw was found in the Red Hat OpenShift AI RHOAI MaaS Gateway. Improper configuration of the Gateway in a model-serving context allows a standard user with low privileges to intercept, read, log, and alter all MaaS model traffic. This includes sensitive information such as access keys, input...

Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

PYSEC-2026-405 Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

PYSEC-2026-423 MLflow Command Injection vulnerability

A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the installmodeldependenciestoenv function. When deploying a model with envmanager=LOCAL, MLflow reads dependency specifications from the model artifact's pythonenv.yaml file and...

MLflow Command Injection vulnerability

A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the installmodeldependenciestoenv function. When deploying a model with envmanager=LOCAL, MLflow reads dependency specifications from the model artifact's pythonenv.yaml file and...

PYSEC-2026-424 Mlflow: Command Injection when serving models with enable_mlserver=True

A command injection vulnerability exists in Mlflow when serving a model with enablemlserver=True. The modeluri is embedded directly into a shell command executed via bash -c without proper sanitization. If the modeluri contains shell metacharacters, such as $ or backticks, it allows for command...

PT-2026-53505

A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the install model dependencies to env function. When deploying a model with env manager=LOCAL, MLflow reads dependency specifications from the model artifact's python env.yaml file an...

PT-2026-53506

A command injection vulnerability exists in Mlflow when serving a model with enable mlserver=True. The model uri is embedded directly into a shell command executed via bash -c without proper sanitization. If the model uri contains shell metacharacters, such as $ or backticks, it allows for comman...

CVE-2026-31238

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

EUVD-2026-29561

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

GHSA-XP5Q-5Q7G-Q26R Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

CVE-2026-31238

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

CVE-2026-31238

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

CVE-2026-31238: Deserialization of Untrusted Data

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

CVE-2026-31238

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters,...