Langflow versions before 1.8.2 allow unauthenticated remote code execution via the '/api/v1/build_public_tmp/{flow_id}/flow' endpoint. Attacker-supplied flow data with arbitrary Python code in node definitions is passed to exec() without sandboxing, enabling code execution without authentication. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible H2O Flow instance on the target application. H2O Flow is an open-source user interface for H2O, an open-source, distributed and scalable machine learning and predictive analytics platform. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible Open WebUI instance on the target application. Open WebUI offer an extensible web application designed for various LLM while offering a feature-rich environment. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible 'llms.txt' file on the target application. The 'llms.txt' file is a proposal designed to provide LLM-friendly content written in markdown for LLMs usage. This detection is included in the AI and LLM category.

By default, MLflow does not require authentication to access the application. When enabling authentication, MLflow will enforce a basic authentication with default credentials. If not updated, a remote and unauthenticated attacker could access the MLflow UI and peform arbitrary actions on it. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible Deep Chat chatbot on the target application. Deep Chat is an open-source framework for building AI chatbots that can be integrated into websites and applications. This detection is included in the AI and LLM category.

H2O Flow is an open-source user interface for H2O, an open-source, distributed and scalable machine learning and predictive analytics platform. By default, H2O Flow does not require authentication to access the application. This allows an attacker to access sensitive data. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible Quivr instance on the target application. Quivr is RAG Framework specialized for building GenAI Second Brains and allows discussion with a variety of documents using different LLM models. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible NextChat (formerly ChatGPT-Next-Web) instance on the target application. NextChat is a collection of tools to help developers build their own AI service around most popular LLMs. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible OpenAssistantGPT chatbot on the target application. OpenAssistantGPT is community open-Source SaaS for crafting/building/creating chatbots with OpenAI's assistant API that you can add to your website. This detection is included in the AI and LLM category.

ModelContextProtocol (MCP) servers using SSE (Server-Sent Events) transport mode are prone to DNS rebinding attacks when they do not enforce strict verification of both the 'Origin' and 'Host' headers. This vulnerability allows an attacker to bypass same-origin policies, potentially leading to unauthorized access to sensitive data or actions on behalf of the user in the context of the vulnerable MCP server.

This detection is included in the AI and LLM category.

Model Context Protocol (MCP) Server Tool Poisoning occurs when malicious actors manipulate tool configurations or metadata on a malicious MCP server. This can lead to the execution of unauthorized commands, data corruption, or the deployment of malicious tools. Such vulnerabilities are particularly dangerous in AI development environments, where poisoned tools can compromise the integrity of the development process and lead to further exploitation. This detection is included in the AI and LLM category.

Model Context Protocol (MCP) Server Prompt Injection occurs when malicious actors use tools response to inject malicious prompts to the calling LLM through the MCP client. This can lead to the execution of unauthorized commands, data corruption, or the deployment of malicious tools. Such vulnerabilities are particularly dangerous in AI development environments, where malicious tools can compromise the integrity of the development process and lead to further exploitation. This detection is included in the AI and LLM category.

This is an informational plugin to inform the user that the scanner has detected a publicly accessible AnythingLLM instance on the target application. AnythingLLM let you choose between different LLM or vector database to use and allow to convert any document or content into references that the selected language model can use while chatting. This detection is included in the AI and LLM category.

NextChat (formerly ChatGPT-Next-Web) versions prior to 2.12.4 are vulnerable to Server-Side Request Forgery (SSRF) and Cross-Site Scripting attacks, allowing remote and unauthenticated attacker to make the vulnerable instance issue arbitrary requests on both external or internal assets through the '/api/webdav' endpoint or to execute JavaScript in the application users browsers context. This detection is included in the AI and LLM category.

The scanner detected the presence of a Large Language Model (LLM) on the target application. LLMs are advanced AI models capable of understanding and generating human-like text based on the input they receive. They are commonly used in various applications, including chatbots, virtual assistants, content generation, and more.

The presence of an LLM can introduce unique security considerations, such as data privacy concerns, potential for generating misleading or harmful content, and vulnerabilities specific to AI models.

This detection is included in the AI and LLM category.

ID	名称	产品	系列	发布时间	最近更新时间	严重程度
115176	Langflow < 1.8.2 Unauthenticated Remote Code Execution	Web App Scanning	Artificial Intelligence	2026/3/27	2026/3/27	critical
114367	H2O Flow Detected	Web App Scanning	Artificial Intelligence	2024/7/18	2024/7/18	info
114304	Open WebUI Detected	Web App Scanning	Artificial Intelligence	2024/6/20	2024/6/20	info
114883	Llms.txt File Detected	Web App Scanning	Artificial Intelligence	2025/6/11	2025/6/11	info
114323	MLflow Default Credentials	Web App Scanning	Artificial Intelligence	2024/6/26	2024/6/26	critical
115115	Deep Chat Chatbot Detected	Web App Scanning	Artificial Intelligence	2026/1/21	2026/1/21	info
114969	H2O Flow Unauthenticated Access	Web App Scanning	Artificial Intelligence	2025/9/26	2025/9/26	critical
114305	Quivr Detected	Web App Scanning	Artificial Intelligence	2024/6/20	2024/6/20	info
114307	NextChat Detected	Web App Scanning	Artificial Intelligence	2024/6/20	2024/6/20	info
115116	OpenAssistantGPT Chatbot Detected	Web App Scanning	Artificial Intelligence	2026/1/28	2026/1/28	info
114885	MCP Server SSE DNS Rebinding	Web App Scanning	Artificial Intelligence	2025/6/20	2025/7/3	medium
114921	MCP Server Tool Poisoning	Web App Scanning	Artificial Intelligence	2025/7/18	2025/7/18	high
114928	MCP Server Prompt Injection	Web App Scanning	Artificial Intelligence	2025/7/31	2025/7/31	high
114303	AnythingLLM Detected	Web App Scanning	Artificial Intelligence	2024/6/20	2024/6/20	info
114326	NextChat < 2.12.4 Server-Side Request Forgery	Web App Scanning	Artificial Intelligence	2024/6/24	2024/6/24	high
114959	LLM Detected	Web App Scanning	Artificial Intelligence	2025/9/9	2025/9/9	info

检测

插件搜索

critical

info

info

info

critical

info

critical

info

info

info

medium

high

high

info

high

info