AI Sec Watch

EmailGPT has a prompt injection vulnerability (a technique where attackers hide malicious instructions in their input to trick the AI) that allows anyone with access to the service to manipulate it into leaking its internal system prompts or executing unintended commands. Attackers can exploit this by submitting specially crafted requests that trick the service into providing harmful information or performing actions it wasn't designed to do.

A workflow file (a set of automated tasks) in the Gradio project has a security flaw where it runs code from external copies of the repository without proper safety checks, allowing attackers to steal sensitive secrets (like API keys and authentication tokens). This happens because the workflow trusts and executes code from forks (unauthorized copies of the project) in an environment that has access to the main repository's secrets.

CVE-2024-37061 is a remote code execution vulnerability (the ability for an attacker to run commands on someone else's system) in MLflow (a machine learning platform) version 1.11.0 and newer. An attacker can create a malicious MLproject file that executes arbitrary code when a user runs it on their computer.

CVE-2024-37060 is a vulnerability in MLflow (a machine learning platform) version 1.27.0 and newer where deserialization of untrusted data (the process of converting received data back into usable objects without checking if it's safe) can occur. A malicious Recipe (a workflow template in MLflow) could exploit this to execute arbitrary code (run any commands) on a user's computer when the Recipe is run.

CVE-2024-37059 is a vulnerability in MLflow (a platform for managing machine learning workflows) version 0.5.0 and newer where deserialization of untrusted data (converting data from an external format into usable code without verifying it's safe) can occur. An attacker can upload a malicious PyTorch model (a type of machine learning model file) that executes arbitrary code (runs any commands they choose) on a user's computer when the model is opened or used.

CVE-2024-37058 is a vulnerability in MLflow (a platform for managing machine learning workflows) version 2.5.0 and newer that allows deserialization of untrusted data (the process of converting data from storage into usable objects without checking if it's safe). An attacker can upload a malicious Langchain AgentExecutor model (a type of AI component) that runs arbitrary code on a user's system when that user interacts with it.

CVE-2024-37057 is a vulnerability in MLflow (an open-source machine learning platform) versions 2.0.0rc0 and newer that allows deserialization of untrusted data (converting data from an untrusted source back into executable code). An attacker could upload a malicious TensorFlow model (a type of machine learning model) that runs arbitrary code (any commands an attacker chooses) on a user's computer when the model is loaded or used.

CVE-2024-37056 is a vulnerability in MLflow (a machine learning platform) version 1.23.0 and newer that allows deserialization of untrusted data (loading and executing code from data that hasn't been verified as safe). An attacker can upload a malicious LightGBM or scikit-learn model (machine learning libraries) that runs arbitrary code (any commands the attacker chooses) on a user's computer when the model is opened.

CVE-2024-37055 is a vulnerability in MLflow (a machine learning platform) versions 1.24.0 and newer where deserialization of untrusted data (the process of converting saved data back into usable objects without checking if it's safe) can occur. This allows an attacker to upload a malicious pmdarima model (a machine learning model for time-series forecasting) that runs arbitrary code (any commands the attacker chooses) on a user's computer when the model is loaded and used.