13775 matches found
Anthropic Slack Model Context Protocol Server ๅฎๅ จๆผๆด
Anthropic Slack Model Context Protocol Server is an open standard protocol for linking large language models from Anthropic. A security vulnerability exists in Anthropic Slack Model Context Protocol Server that stems from mishandling of data, which could lead to data disclosure...
PT-2025-27630 ยท Anthropic ยท Slack Model Context Protocol (Mcp) Server
Name of the Vulnerable Software and Affected Versions: Anthropicโs Slack Model Context Protocol MCP Server affected versions not specified Description: A data exfiltration issue exists in the deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using t...
Model Context Protocol Servers ่ทฏๅพ้ๅๆผๆด
Model Context Protocol Servers is a large model context protocol server from Model Context Protocol open source. A path traversal vulnerability exists in Model Context Protocol Servers versions prior to 0.6.4 and prior to 2025.7.01, which stems from the fact that prefix matching can lead to...
Model Context Protocol Servers ๅ็ฝฎ้พๆฅๆผๆด
Model Context Protocol Servers is a large model context protocol server from Model Context Protocol open source. A back-linking vulnerability exists in Model Context Protocol Servers versions prior to 0.6.4 and prior to 2025.7.01, which stems from the fact that symbolic links can lead to accessin...
CVE-2025-6920 Ai-inference-server: authentication bypass via unprotected inference endpoint in api
A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/ endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows...
A New Maturity Model for Browser Security: Closing the Last-Mile Risk
Despite years of investment in Zero Trust, SSE, and endpoint protection, many enterprises are still leaving one critical layer exposed: the browser. It's where 85% of modern work now happens. It's also where copy/paste actions, unsanctioned GenAI usage, rogue extensions, and personal devices crea...
PT-2025-27616
Name of the Vulnerable Software and Affected Versions Model Context Protocol Servers Filesystem versions prior to 0.6.4 Model Context Protocol Servers Filesystem versions prior to 2025.7.01 Description An issue exists in the server-filesystem implementation of the Model Context Protocol MCP due t...
CVE-2025-52573
iOS Simulator MCP Server ios-simulator-mcp is a Model Context Protocol MCP server for interacting with iOS simulators. Versions prior to 1.3.3 are written in a way that is vulnerable to command injection vulnerability attacks as part of some of its MCP Server tool definition and implementation. T...
CVE-2025-53098 Roo Code Vulnerable to Potential Remote Code Execution via Model Context Protocol
Roo Code is an AI-powered autonomous coding agent. The project-specific MCP configuration for the Roo Code agent is stored in the .roo/mcp.json file within the VS Code workspace. Because the MCP configuration format allows for execution of arbitrary commands, prior to version 3.20.3, it would hav...
CVE-2025-53098 Roo Code Vulnerable to Potential Remote Code Execution via Model Context Protocol
Roo Code is an AI-powered autonomous coding agent. The project-specific MCP configuration for the Roo Code agent is stored in the .roo/mcp.json file within the VS Code workspace. Because the MCP configuration format allows for execution of arbitrary commands, prior to version 3.20.3, it would hav...
CVE-2025-53098
Roo Code prior to version 3.20.3 stores the MCP configuration in .roo/mcp.json. The MCP config format allows executing arbitrary commands, enabling an attacker who can submit prompts (e.g., via prompt injection) and who has MCP enabled and auto-approve file writes turned on to inject a malicious ...
OESA-2025-1701 libxml2 security update
This library allows to manipulate XML files. It includes support to read, modify and write XML and HTML files. There is DTDs support this includes parsing and validation even with complex DtDs, either at parse time or later once the document has been modified. The output can be a simple SAX strea...
CVE-2024-51977
An unauthenticated attacker who can access either the HTTP service TCP port 80, the HTTPS service TCP port 443, or the IPP service TCP port 631, can leak several pieces of sensitive information from a vulnerable device. The URI path /etc/mntinfo.csv can be accessed via a GET request and no...
Adversarial Threats in Quantum Machine Learning: a Survey of Attacks and Defenses
Quantum Machine Learning QML integrates quantum computing with classical machine learning, primarily to solve classification, regression and generative tasks. However, its rapid development raises critical security challenges in the Noisy Intermediate-Scale Quantum NISQ era. This chapter examines...
CVE-2024-51977
An unauthenticated attacker who can access either the HTTP service TCP port 80, the HTTPS service TCP port 443, or the IPP service TCP port 631, can leak several pieces of sensitive information from a vulnerable device. The URI path /etc/mntinfo.csv can be accessed via a GET request and no...
CVE-2024-51977
An unauthenticated attacker who can access either the HTTP service TCP port 80, the HTTPS service TCP port 443, or the IPP service TCP port 631, can leak several pieces of sensitive information from a vulnerable device. The URI path /etc/mntinfo.csv can be accessed via a GET request and no...
CVE-2024-51977
CVE-2024-51977 affects at least one Brother multiโfunction device (notably the MFCโL9570CDW) where an unauthenticated attacker can reach the HTTP/HTTPS/IPP services on ports 80/443/631 and retrieve /etc/mnt_info.csv. The CSV exposes device info including model, firmware version, IP address, and s...
CVE-2024-51977 Unauthenticated leak of sensitive information affecting multiple models from Brother Industries, Ltd., FUJIFILM Business Innovation, Ricoh, Toshiba Tec, and Konica Minolta, Inc.
An unauthenticated attacker who can access either the HTTP service TCP port 80, the HTTPS service TCP port 443, or the IPP service TCP port 631, can leak several pieces of sensitive information from a vulnerable device. The URI path /etc/mntinfo.csv can be accessed via a GET request and no...
Universal and Efficient Detection of Adversarial Data through Nonuniform Impact on Network Layers
Deep Neural Networks DNNs are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against these attacks are relatively understudied. Existing defense...
Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
Memorization in large language models LLMs makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA fine-tuning, a widely adopted parameter-efficient method. In this...