PT-2025-32324

Name of the Vulnerable Software and Affected Versions ExecuTorch versions prior to commit 8f062d3f661e20bb19b24b767b9a9a46e8359f2b Description An integer overflow in the loading of ExecuTorch models can lead to the allocation of smaller-than-expected memory regions. This can potentially result in...

executorch 安全漏洞

executorch is an open source PyTorch deployment tool for PyTorch by pytorch. A security vulnerability exists in executorch that stems from a heap buffer overflow when loading a model, which could lead to code execution...

CVE-2025-8665 agno-agi agno Model Context Protocol mcp.py MultiMCPTools os command injection

A vulnerability, which was classified as critical, has been found in agno-agi agno up to 1.7.5. This issue affects the function MCPTools/MultiMCPTools in the library libs/agno/agno/tools/mcp.py of the component Model Context Protocol Handler. The manipulation of the argument command leads to os...

CVE-2025-8665

CVE-2025-8665 affects agno-agi agno up to 1.7.5. The vulnerability lies in the MCPTools/MultiMCPTools function in libs/agno/agno/tools/mcp.py of the Model Context Protocol Handler, where manipulation of the command argument enables OS command injection. Exploitation can be remote and the vulnerab...

CVE-2025-8665 agno-agi agno Model Context Protocol mcp.py MultiMCPTools os command injection

A vulnerability, which was classified as critical, has been found in agno-agi agno up to 1.7.5. This issue affects the function MCPTools/MultiMCPTools in the library libs/agno/agno/tools/mcp.py of the component Model Context Protocol Handler. The manipulation of the argument command leads to os...

CVE-2025-5197 Regular Expression Denial of Service (ReDoS) in huggingface/transformers

A Regular Expression Denial of Service ReDoS vulnerability exists in the Hugging Face Transformers library, specifically in the converttfweightnametoptweightname function. This function, responsible for converting TensorFlow weight names to PyTorch format, uses a regex pattern /^/^// that can be...

AuthPrint: Fingerprinting Generative Models against Malicious Model Providers

Generative models are increasingly adopted in high-stakes domains, yet current deployments offer no mechanisms to verify the origin of model outputs. We address this gap by extending model fingerprinting techniques beyond the traditional collaborative setting to one where the model provider may a...

agno 命令注入漏洞

agno is an Agno open source full-stack framework for building multi-intelligent body systems with memory, knowledge and reasoning. A command injection vulnerability exists in agno 1.7.5 and earlier versions, which stems from a misbehavior of the MCPTools/MultiMCPTools function in the Model Contex...

Leveraging Large Language Models for SQL Behavior-Based Database Intrusion Detection

Database systems are extensively used to store critical data across various domains. However, the frequency of abnormal database access behaviors, such as database intrusion by internal and external attacks, continues to rise. Internal masqueraders often have greater organizational knowledge,...

The vulnerability in the web interface for managing Microprogramming Software on Intelbras RX 1500 and RX 3000 allows attackers to carry out cross-site scripting attacks.

The vulnerability of the web interface for managing Microprogramming Software on Intelbras RX 1500 and RX 3000 is related to the lack of measures taken to protect the structure of the web page. Exploiting this vulnerability allows a malicious actor to perform cross-site scripting attacks by sendi...

CVE-2025-51060

An issue was discovered in CPUID cpuz.sys 1.0.5.4. An attacker can use DeviceIoControl with the unvalidated parameters 0x9C402440 and 0x9C402444 as IoControlCodes to perform RDMSR and WRMSR, respectively. Through this process, the attacker can modify MSRLSTAR and hook KiSystemCall64. Afterward,...

Arbitrary Code Execution

skops is vulnerable to Arbitrary Code Execution. The vulnerability is due to exploitation of the MethodNode class, which allows unexpected attribute access via dot notation during model loading...

Misconfigurations Are Not Vulnerabilities: The Costly Confusion Behind Security Risks

In SaaS security conversations, "misconfiguration" and "vulnerability" are often used interchangeably. But they're not the same thing. And misunderstanding that distinction can quietly create real exposure. This confusion isn't just semantics. It reflects a deeper misunderstanding of the shared...

Attack the Messages, Not the Agents: a Multi-Round Adaptive Stealthy Tampering Framework for LLM-MAS

Large language model-based multi-agent systems LLM-MAS effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct...

Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning

Network Intrusion Detection Systems NIDS play a crucial role in safeguarding network infrastructure against cyberattacks. As the prevalence and sophistication of these attacks increase, machine learning and deep neural network approaches have emerged as effective tools for enhancing NIDS...

FIRSTNUM JC21A-04 安全漏洞

The FIRSTNUM JC21A-04 is a router from the Chinese company FIRSTNUM. A security vulnerability exists in the FIRSTNUM JC21A-04 version 2.01ME/FN and prior versions, which stems from the SSH service being enabled by default and using root/admin credentials...

Jointelli 5G CPE 21H01 安全漏洞

The Jointelli 5G CPE 21H01 is a router from the Chinese company Jointelli. A security vulnerability exists in the Jointelli 5G CPE 21H01 JY21H01A3v1.36 version, which stems from the presence of OS command injection on multiple endpoints that could lead to the execution of arbitrary commands...

PhishParrot: LLM-Driven Adaptive Crawling to Unveil Cloaked Phishing Sites

Phishing attacks continue to evolve, with cloaking techniques posing a significant challenge to detection efforts. Cloaking allows attackers to display phishing sites only to specific users while presenting legitimate pages to security crawlers, rendering traditional detection systems ineffective...

PT-2025-31846 · Nvidia · Nvidia Triton Inference Server

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server versions affected versions not specified Description: NVIDIA Triton Inference Server for Windows and Linux contains an issue in the Python backend. An attacker could exceed the shared memory limit by sending a...

PT-2025-32169 · Nvidia · Nvidia Triton Inference Server +1

Name of the Vulnerable Software and Affected Versions: NVIDIA Triton Inference Server affected versions not specified Tensor RT backend affected versions not specified Description: The NVIDIA Triton Inference Server and its Tensor RT backend contain an issue where an attacker can trigger an...