AI & LLM Vulnerabilities

CVE-2025-48956 is a Denial of Service vulnerability (a type of attack that makes a service unavailable) in vLLM, an inference and serving engine for large language models. Versions 0.1.0 through 0.10.1.0 are vulnerable to crashing when someone sends an HTTP GET request with an extremely large header, which exhausts the server's memory. This attack requires no authentication, so anyone on the internet can trigger it.

claude-code-router is a tool that directs Claude Code requests to different AI models. The software has a security flaw in its CORS (Cross-Origin Resource Sharing, which controls what websites can access a service) configuration that could allow attackers to steal user API keys (credentials that grant access to services) and sensitive data from untrusted websites.

Claude Code is a tool that lets AI assistants write and run code on your computer. Before version 1.0.4, attackers could trick the tool into reading files and sending their contents over the internet without asking you first, because the tool had a list of allowed commands that was too broad. Exploiting this attack requires the attacker to insert malicious instructions into the conversation with Claude Code.

NVIDIA Merlin Transformers4Rec contains a vulnerability in one of its Python dependencies that allows attackers to inject malicious code (code injection, where an attacker inserts unauthorized commands into a program). A successful attack could lead to code execution (running unauthorized commands on a system), privilege escalation (gaining higher-level access rights), information disclosure (exposing sensitive data), and data tampering (unauthorized modification of data).

CVE-2025-53773 is a command injection vulnerability (a flaw where special characters in user input are not properly filtered, allowing an attacker to run unauthorized commands) found in GitHub Copilot and Visual Studio that lets an unauthorized attacker execute code on a user's local computer. The vulnerability exploits improper handling of special elements in commands, potentially through prompt injection (tricking the AI by hiding malicious instructions in its input).

Zed, a multiplayer code editor, had a vulnerability before version 0.197.3 where an AI agent could bypass permission checks and achieve RCE (remote code execution, where an attacker can run commands on a system they don't own) by creating or modifying configuration files without user approval. This allowed the AI agent to execute arbitrary commands on a victim's machine.

CVE-2025-8747 is a safe mode bypass vulnerability in Keras (a machine learning library) versions 3.0.0 through 3.10.0 that allows an attacker to run arbitrary code (execute any commands they want) on a user's computer by tricking them into loading a specially designed `.keras` model file. The vulnerability has a CVSS score (severity rating) of 8.6, indicating it is a high-risk security problem.

The skops Python library (used for sharing scikit-learn machine learning models) has a security flaw in versions 0.12.0 and earlier where the Card.get_model function can accidentally use joblib (a less secure loading method) instead of skops' safer approach. Joblib allows arbitrary code execution (running any code during model loading), which could let attackers run malicious code if they trick users into loading a specially crafted model file. This bypasses the security checks that skops normally provides.

CVE-2025-53787 is an information disclosure vulnerability in Microsoft 365 Copilot BizChat that stems from improper neutralization of special elements used in commands (command injection, where attackers manipulate input to execute unintended commands). The vulnerability allows unauthorized access to sensitive information, though specific attack details are not provided in this source.

NVIDIA Triton Inference Server (software that runs AI models on Windows and Linux) has a vulnerability where an attacker could send a specially crafted request that causes the server to try allocating an extremely large amount of memory, resulting in a crash (segmentation fault, which is when a program stops running due to a memory error). This could lead to a denial of service attack (making the service unavailable to legitimate users).

NVIDIA Triton Inference Server for Windows and Linux has a vulnerability where an attacker could cause an integer overflow (a bug where a number becomes too large for the system to handle properly) by sending specially crafted inputs, potentially leading to denial of service (making the service unavailable) and data tampering. The severity rating from NIST has not yet been assigned.

NVIDIA Triton Inference Server (software that runs AI models on servers) for Windows and Linux has a vulnerability where an attacker could send specially crafted input that causes an integer overflow (when a number calculation exceeds the maximum value a computer can store, causing unexpected behavior), potentially leading to a denial of service attack (making the service unavailable to legitimate users).