AI & LLM Vulnerabilities

CVE-2024-45855 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.10.2.0 and newer where deserialization of untrusted data (converting data from an external format into code without checking if it's safe) can occur. An attacker can upload a malicious 'inhouse' model and use the 'finetune' feature to run arbitrary code (any commands they want) on the server.

CVE-2024-45854 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.10.3.0 and newer where deserialization of untrusted data (converting data from an external format back into executable code without checking if it's safe) allows an attacker to upload a malicious model that runs arbitrary code (any commands the attacker wants) on the server when a describe query is executed on it.

CVE-2024-45853 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.10.2.0 and newer where deserialization of untrusted data (the process of converting received data back into usable objects without checking if it's safe) allows an attacker to upload a malicious model that runs arbitrary code on the server when making predictions. This is a serious flaw because it gives attackers full control to execute whatever commands they want on the affected system.

CVE-2024-45852 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.3.2.0 and newer that allows deserialization of untrusted data (converting untrusted incoming data back into executable code). An attacker can upload a malicious model that runs arbitrary code (any commands they choose) on the server when someone interacts with it.

CVE-2024-38206 is a vulnerability in Microsoft Copilot Studio where an authenticated attacker (someone with valid login credentials) can bypass SSRF protection (security that prevents a server from being tricked into making unwanted network requests) to leak sensitive information over a network.

A vulnerability in the stitionai/devika AI project allows attackers to read sensitive files on a computer through prompt injection (tricking an AI by hiding malicious instructions in its input). The problem occurs because Google Gemini's safety filters were disabled, which normally prevent harmful outputs, leaving the system open to commands like reading `/etc/passwd` (a file containing user account information).

Haystack is a framework for building applications with LLMs (large language models) and AI tools, but versions before 2.3.1 have a critical vulnerability where attackers can execute arbitrary code if they can create and render Jinja2 templates (template engines that generate dynamic text). This affects Haystack clients that allow users to create and run Pipelines, which are workflows that process data through multiple steps.

A bug in TensorFlow (an open source platform for building machine learning models) causes a segfault (a crash where the program tries to access memory it shouldn't) when the `array_ops.upper_bound` function receives input that is not a rank 2 tensor (a two-dimensional array of numbers).

Langflow versions before 1.0.13 have a privilege escalation vulnerability (a security flaw where an attacker gains higher access rights than they should have) that lets a remote attacker with low privileges become a super admin by sending a specially crafted request to the '/api/v1/users' endpoint using mass assignment (a technique where an attacker modifies multiple fields at once by exploiting how the application handles user input).