AI Sec Watch

OpenAI is planning to release a smart speaker device that lets users speak to ChatGPT and includes a camera and sensors to understand the surrounding environment, though it will have no screen. The device will have a rechargeable battery for portability and smart home control features, though this announcement comes amid legal disputes with Apple over alleged hardware theft.

NVIDIA TensorRT-LLM (a tool for running large language models efficiently) contains a vulnerability in its OpenAI-compatible API where an attacker could trigger a reachable assertion (a failed safety check in the code) in the sampler thread, potentially causing the system to crash. This vulnerability could lead to a denial of service attack (making the service unavailable to legitimate users).

NVIDIA TensorRT-LLM (a tool for running large language models efficiently on NVIDIA GPUs) has a vulnerability in its OpenAI-compatible inference API that allows attackers to request unlimited GPU resources without restrictions. This could cause a denial of service (making the system unavailable to legitimate users) by exhausting the GPU's memory and processing power.

NVIDIA TensorRT-LLM for Linux has a vulnerability in its unpickler (a tool that converts serialized data back into usable objects) that allows local attackers to deserialize untrusted data. A successful attack could lead to code execution, privilege escalation, data tampering, and information disclosure.

In n8n-mcp (a tool that connects AI models to workflows) running in multi-tenant HTTP mode (where multiple separate users share one server), an authenticated user could bypass access controls and read or delete workflow backups stored in the default single-tenant scope instead of being restricted to their own workspace. This could expose sensitive workflow configuration information.

CVE-2026-47482 is a memory leak vulnerability (a bug where a program fails to free up memory it's no longer using) in NVIDIA Triton Inference Server for Linux that allows attackers to cause a denial of service (making a service unavailable to legitimate users). The vulnerability stems from the software not properly releasing memory after it's finished using it.

CVE-2026-47481 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows attackers to bypass authentication (security checks that verify a user's identity) through an alternative path or channel. If successfully exploited, this flaw could let attackers run their own code on the system, gain higher-level access, steal information, or modify data.

CVE-2026-47480 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to trigger an uncaught exception (an error that the program doesn't handle properly), potentially causing a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a detailed assessment has not yet been provided.

CVE-2026-47479 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to cause uncontrolled resource consumption (using up all available computing power or memory), potentially leading to a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a complete assessment from NIST has not yet been provided.