256 matches found
CVE-2026-85661 excel-mcp-server 0.1.8 Arbitrary File Read/Write via stdio mode
excel-mcp-server 0.1.8 fails to enforce path confinement in stdio mode when EXCELFILESPATH is unset, allowing attackers to read and write arbitrary files. Attackers can supply unchecked file paths to read and write tools to access any file accessible to the process...
CVE-2026-85623 goose 1.37.0 Arbitrary Command Execution via Recipe Extensions
goose 1.37.0 executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. Attackers can distribute malicious recipes that execute shell commands as the user running goose, bypassing the recipe security scan which does not inspect extensions or retry...
CVE-2026-85623 goose 1.37.0 Arbitrary Command Execution via Recipe Extensions
goose 1.37.0 executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. Attackers can distribute malicious recipes that execute shell commands as the user running goose, bypassing the recipe security scan which does not inspect extensions or retry...
CVE-2026-85623
goose v1.37.0 (by aaif-goose) contains an arbitrary command execution flaw in its recipe subsystem. The vulnerable components are stdio extensions and retry.checks within recipes, which are executed without passing through the recipe security scan—creating a bypass for attackers who distribute ma...
EUVD-2026-71230
goose 1.37.0 executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. Attackers can distribute malicious recipes that execute shell commands as the user running goose, bypassing the recipe security scan which does not inspect extensions or retry...
CVE-2026-85623 goose 1.37.0 Arbitrary Command Execution via Recipe Extensions
goose 1.37.0 executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. Attackers can distribute malicious recipes that execute shell commands as the user running goose, bypassing the recipe security scan which does not inspect extensions or retry...
CVE-2026-85661: Improper Limitation of a Pathname to a Restricted Directory
excel-mcp-server 0.1.8 fails to enforce path confinement in stdio mode when EXCELFILESPATH is unset, allowing attackers to read and write arbitrary files. Attackers can supply unchecked file paths to read and write tools to access any file accessible to the process...
PT-2026-85547
Name of the Vulnerable Software and Affected Versions goose versions prior to 1.38.0 Description The software executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. This occurs because the recipe security scan skips these two fields, allowing...
CVE-2026-85623: Improper Control of Generation of Code
goose 1.37.0 executes arbitrary commands from recipe stdio extensions and retry.checks without security inspection. Attackers can distribute malicious recipes that execute shell commands as the user running goose, bypassing the recipe security scan which does not inspect extensions or retry...
PT-2026-85554
excel-mcp-server 0.1.8 fails to enforce path confinement in stdio mode when EXCEL FILES PATH is unset, allowing attackers to read and write arbitrary files. Attackers can supply unchecked file paths to read and write tools to access any file accessible to the process...
EUVD-2026-64016
Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE...
CVE-2026-79748
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.15, the POST /api/servers and PUT /api/servers/:name endpoints in MCPHub create/update MCP server configurations a...
CVE-2026-79748
MCPHub , a hub for centrally managing and orchestrating multiple MCP servers/APIs, contains a command injection vulnerability in the POST /api/servers and PUT /api/servers/:name endpoints prior to version 0.12.15. These endpoints spawn configured stdio processes via child_process.spawn but lack a...
CVE-2026-79748 MCPHub: Authenticated non-admin user achieves RCE via POST /api/servers (missing authorization on stdio command/args)
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.15, the POST /api/servers and PUT /api/servers/:name endpoints in MCPHub create/update MCP server configurations a...
CVE-2026-79748 MCPHub: Authenticated non-admin user achieves RCE via POST /api/servers (missing authorization on stdio command/args)
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.15, the POST /api/servers and PUT /api/servers/:name endpoints in MCPHub create/update MCP server configurations a...
Command Injection
Overview chainlit is a Build Conversational AI. Affected versions of this package are vulnerable to Command Injection through the validatemcpcommand flow in backend/chainlit/mcp.py and the /mcp stdio connect handler. An attacker can execute arbitrary OS commands on the server by sending a POST /m...
CVE-2026-45018
Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the...
GHSA-W3FX-MC44-MF6J Chainlit has command injection via MCP stdio transport that allows unauthenticated remote code execution
Am I affected? Only if your deployment sets features.mcp.enabled = true in .chainlit/config.toml. MCP has been disabled by default since v2.7.0, so most Chainlit deployments are not affected. No authentication is required: /mcp is reachable by any client that can open a session. Summary When MCP ...
Chainlit has command injection via MCP stdio transport that allows unauthenticated remote code execution
Am I affected? Only if your deployment sets features.mcp.enabled = true in .chainlit/config.toml. MCP has been disabled by default since v2.7.0, so most Chainlit deployments are not affected. No authentication is required: /mcp is reachable by any client that can open a session. Summary When MCP ...
CVE-2026-45018 Chainlit: Command injection via MCP stdio transport allows unauthenticated remote code execution
Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the...