CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

CVE-2026-34163

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

CVE-2026-34163 Server-Side Request Forgery via MCP Tools Endpoint in FastGPT

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

EUVD-2026-17447

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

EUVD-2026-17357

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

CVE-2026-4399

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

Arbitrary Code Execution.

@anthropic-ai/claude-code is vulnerable to Arbitrary code execution. The vulnerability is due to improper parsing of shell commands involving $IFS and short CLI flags, which allows an attacker to bypass read-only validation and execute arbitrary code by injecting untrusted content into the contex...

CVE-2026-4399 Multiple vulnerabilities in 1millionbot Millie chatbot

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques formulating a question in such a way that, upon receiving an affirmative response 'true', the model executes the injected instruction,...

PT-2026-29219

Name of the Vulnerable Software and Affected Versions 1millionbot Millie chatbot affected versions not specified Description A prompt injection issue exists in the 1millionbot Millie chatbot. This occurs when a user bypasses chat restrictions using Boolean prompt injection techniques, constructin...

PT-2026-29263

FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP Model Context Protocol tools endpoints /api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the...

Efficient Software Vulnerability Detection Using Transformer-Based Models

Detecting software vulnerabilities is critical to ensuring the security and reliability of modern computer systems. Deep neural networks have shown promising results on vulnerability detection, but they lack the capability to capture global contextual information on vulnerable code. To address th...

CVE-2026-29870

A directory traversal vulnerability in the agentic-context-engine project versions up to 0.7.1 allows arbitrary file writes via the checkpointdir parameter in OfflineACE.run. The savetofile method in ace/skillbook.py fails to normalize or validate filesystem paths, allowing traversal sequences to...

PT-2026-29377

Name of the Vulnerable Software and Affected Versions SiYuan versions prior to 3.6.2 Description A security flaw exists in SiYuan that allows a malicious website to achieve Remote Code Execution RCE on a desktop system running the application. This is possible due to a permissive CORS policy...

MCP Java SDK security vulnerabilities

The MCP Java SDK is an open-source standard protocol SDK for integrating AI models and tools with Java applications, developed under the Model Context Protocol. Versions of the MCP Java SDK prior to 1.0.1 and 1.1.1 contained security vulnerabilities, which were caused by hardcoded wildcard CORS...

Agentic Context Engine security vulnerability

Agentic Context Engine is an AI proxy learning and optimization framework developed by Kayba. Versions of Agentic Context Engine 0.7.1 and earlier contained security vulnerabilities. These vulnerabilities were caused by a directory traversal vulnerability in the checkpointdir parameter, which cou...

CVE-2026-29870

A directory traversal vulnerability in the agentic-context-engine project versions up to 0.7.1 allows arbitrary file writes via the checkpointdir parameter in OfflineACE.run. The savetofile method in ace/skillbook.py fails to normalize or validate filesystem paths, allowing traversal sequences to...

PT-2026-29270

Name of the Vulnerable Software and Affected Versions agentic-context-engine versions prior to 0.7.2 Description A directory traversal issue allows arbitrary file writes through the checkpoint dir parameter in the OfflineACE.run function. The save to file method in ace/skillbook.py does not...

CVE-2026-34449: Permissive Cross-domain Policy with Untrusted Domains

SiYuan is a personal knowledge management system. Prior to version 3.6.2, a malicious website can achieve Remote Code Execution RCE on any desktop running SiYuan by exploiting the permissive CORS policy Access-Control-Allow-Origin: + Access-Control-Allow-Private-Network: true to inject a JavaScri...

CVE-2026-29870: Improper Limitation of a Pathname to a Restricted Directory

A directory traversal vulnerability in the agentic-context-engine project versions up to 0.7.1 allows arbitrary file writes via the checkpointdir parameter in OfflineACE.run. The savetofile method in ace/skillbook.py fails to normalize or validate filesystem paths, allowing traversal sequences to...