AI Sec Watch

A CSRF vulnerability (cross-site request forgery, where an attacker tricks a user into performing unwanted actions on a website) exists in the Signup feature of MLflow versions 2.17.0 to 2.20.1, allowing attackers to create unauthorized accounts. This could enable an attacker to perform malicious actions while appearing to be a legitimate user.

MLflow version 2.17.2 has a vulnerability in its `/graphql` endpoint (a web interface for querying data) that allows attackers to perform a denial of service attack (making a service unavailable) by sending large batches of repeated queries. This exhausts all the workers (processes handling requests) that MLflow has available, preventing the application from responding to legitimate requests.

Ollama (an AI model framework) versions 0.3.14 and earlier have a vulnerability where a malicious user can upload a specially crafted GGUF model file (a format for storing AI models) that causes a division by zero error (when code tries to divide a number by zero, crashing the program) in the ggufPadding function, crashing the server and making it unavailable (a Denial of Service attack).

A vulnerability in Ollama (an AI model software) version 0.3.14 and earlier allows an attacker to upload a specially crafted GGUF model file (a format for storing AI models) that tricks the server into using unlimited memory, causing a denial of service (DoS, a situation where a system becomes unavailable to users). The vulnerability stems from the server not properly limiting how much memory it allocates when processing model files.

CVE-2025-0312 is a vulnerability in Ollama (a tool for running AI models locally) versions 0.3.14 and earlier that allows an attacker to upload a malicious GGUF model file (a specific format for storing AI model weights). When the server processes this file, it crashes due to a null pointer dereference (trying to access memory that doesn't contain valid data), which can be exploited remotely to cause a denial of service attack (making the service unavailable to legitimate users).

CVE-2025-0187 is a denial of service (DoS, an attack that makes a service unavailable) vulnerability in Gradio version 0.39.1's file upload feature. An attacker can send a request with an extremely large filename, which the server doesn't handle properly, causing it to become overwhelmed and stop responding to legitimate users.

CVE-2024-9070 is a deserialization vulnerability (a security flaw where untrusted data is converted back into executable code) in BentoML versions 1.3.4.post1 and earlier that affects the runner server component. An attacker can exploit this by setting specific parameters to execute arbitrary code (any commands they choose) on the affected server, causing severe damage.

BentoML version v1.3.4post1 has a vulnerability that allows attackers to cause a denial of service (DoS, making a service unavailable by overwhelming it with requests) by adding extra characters like dashes to the end of a multipart boundary (the delimiter that separates different parts of an HTTP request). This causes the server to waste resources processing these characters repeatedly, and since it requires no authentication or user interaction, it affects all users of the service.

vllm version 0.6.0 has a vulnerability in its RPC server (a system that allows remote programs to request operations) where the _make_handler_coro() function uses cloudpickle.loads() to process incoming messages without checking if they're safe first. An attacker can send malicious serialized data (pickle is a format for converting Python objects into bytes) to execute arbitrary code on the affected system.