LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

The proliferation of Low-Rank Adaptation LoRA models has democratized personalized text-to-image generation, enabling users to share lightweight models e.g., personal portraits on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs c...

Model Context Protocol Python SDK 安全漏洞

Model Context Protocol Python SDK is a Model Context Protocol open source development tool for Model Context Protocol servers and clients. A security vulnerability exists in the Model Context Protocol Python SDK prior to version 1.9.4, which stems from an unhandled exception when handling malform...

Cross-site Scripting (XSS)

Overview Affected versions of this package are vulnerable to Cross-site Scripting XSS via the shortdesc property, which is inserted into the DOM as raw HTML without proper escaping. An attacker can execute arbitrary JavaScript in the context of the user's browser by injecting malicious content...

Dependacy chain attack through hijacking broken github repository at https://github.com/huggingface/transformers/blob/main/src/\ntransformers/models/fuyu/\nconvert_fuyu_model_weights_to_hf.py

Description Type: Dependency Chain Attack through hijacking broken github repository Risk: High Allows arbitrary code execution in model conversion workflows Affected Asset: https://github.com/adept-ai-labs/adept-inference Broken URL in Hugging Face Transformers Root Cause The Hugging Face...

CVE-2025-53109

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...

CVE-2025-53110

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

Improper Neutralization of Input Used for LLM Prompting

Overview @modelcontextprotocol/server-slack is a MCP server for interacting with Slack Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the automatic link unfurling process. An attacker can access sensitive information by manipulating...

CVE-2025-53109 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Prefix Matching and Symlink Handling

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...

CVE-2025-53109

CVE-2025-53109 affects Model Context Protocol Servers (Filesystem MCP Server). Versions prior to 0.6.4 or 2025.7.01 allow access to unintended files via symlinks within allowed directories due to a path-validation bypass (symlink handling) and weak error handling. In practice, this could enable r...

CVE-2025-53109 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Prefix Matching and Symlink Handling

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...

CVE-2025-53110 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Colliding Path Prefix

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

CVE-2025-53110

CVE-2025-53110 affects Model Context Protocol Servers (Filesystem MCP Server). A path validation bypass allows accessing unintended files when the allowed-directory prefix collides with other paths, prior to versions 0.6.4 or 2025.7.01. The issue enables directory containment bypass and potential...

CVE-2025-53110 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Colliding Path Prefix

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

CVE-2025-53110 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Colliding Path Prefix

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

CVE-2025-34072

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embeddin...

Anthropic Slack Model Context Protocol Server 安全漏洞

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...

Model Context Protocol Servers 后置链接漏洞

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...

Model Context Protocol Servers 路径遍历漏洞

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...

PT-2025-27630 · Anthropic · Slack Model Context Protocol (Mcp) Server

Name of the Vulnerable Software and Affected Versions: Anthropic’s 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...

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...