CVE-2026-18976

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

CVE-2026-18976

The CVE affects NousResearch hermes-agent up to version 0.16.0. The vulnerability impacts the get_tool_definitions function in agent/agent_init.py within the disabled_toolsets Handler, where manipulation leads to incorrect privilege assignment. The issue could be exploited remotely and an exploit...

EUVD-2026-53698

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

CVE-2026-18976

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

CVE-2026-18976 NousResearch hermes-agent disabled_toolsets agent_init.py get_tool_definitions privileges assignment

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

Attacking the MCP Trust Boundary

Every secure API draws a line between code and data. HTTP separates headers from bodies. SQL has prepared statements. Even email distinguishes the envelope from the message. The Model Context Protocol MCP, the fast-growing standard for connecting AI agents to external services, inherits that gap...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

CVE-2026-39891

PraisonAI’s multi-agent system contains a template injection in the create_agent_centric_tools() function prior to version 4.5.115. Tools such as acp_create_file process file content via template rendering, and user input from agent.start() could be rendered as template expressions instead of bei...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

EUVD-2026-20639

PraisonAI has Template Injection in Agent Tool Definitions...

PraisonAI has Template Injection in Agent Tool Definitions

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user inpu...

Command Injection

adb-mcp Server is vulnerable to Command Injection. The vulnerability is due to improper handling of user-supplied input in certain MCP Server tool definitions and implementations, which allows an attacker to inject and execute arbitrary system commands...

ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by Using OAuth-Enhanced Tool Definitions and Policy-Based Access Control

The Model Context Protocol MCP plays a crucial role in extending the capabilities of Large Language Models LLMs by enabling integration with external tools and data sources. However, the standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull...