CVE-2026-108586

1MCP Agent @1mcp/agent 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enforcement using negated advanced tag-filter expressions. Attackers holding a single-tag token can send a filter like not to list and invoke...

EUVD-2026-96373

1MCP Agent @1mcp/agent 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enforcement using negated advanced tag-filter expressions. Attackers holding a single-tag token can send a filter like not to list and invoke...

CVE-2026-108586

The 1MCP Agent (@1mcp/agent) versions 0.20.0 through 0.39.0 are vulnerable to an incorrect authorization issue (CWE-863). This flaw allows authenticated clients to bypass OAuth tag-scope enforcement by utilizing negated advanced tag-filter expressions . Specifically, an attacker possessing a toke...

EUVD-2026-44638

PraisonAI: MCP HTTP-stream transport is unauthenticated by default, exposing tool enumeration and an unvalidated tool-call surface...

CVE-2026-80337 Unauthorized Cross-Chatbot Tool Invocation in HAVELSAN's Sef - AI Chatbot Platform

Missing Authorization vulnerability in HAVELSAN Inc. Sef - AI Chatbot Platform allows Accessing Functionality Not Properly Constrained by ACLs. This issue affects Sef - AI Chatbot Platform: before 2.1. NOTE: The vendor was contacted and it was learned that the product is not supported...

PT-2026-105836

Summary ENABLED TOOLS and TOOLSETS filters are enforced at tools/list time only. tools/call dispatches from the full unfiltered tool registry 73 tools. Any user with access to the server endpoint that knows a tool name can invoke it directly. Tool names are not secret since mcp-atlassian is open...

CVE-2026-100573

OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...

CVE-2026-100573

OpenClaw versions prior to 2026.8.1 are vulnerable to a sandbox policy bypass within the MCP loopback component . This flaw enables sandboxed coding-agent sessions to circumvent the sandbox.tools.deny policy, allowing them to list and invoke tools that were explicitly restricted by the operator. ...

CVE-2026-100573

OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...

CVE-2026-100545

OpenClaw npm package "openclaw" before 2026.8.1 incorrectly enforces sender tool policies during session-memory filename generation. In affected versions, filename generation created an embedded helper that retained tools which the originating sender's policy had removed. When session-memory...

PT-2026-99235

Name of the Vulnerable Software and Affected Versions OpenClaw versions 2026.5.1 through 2026.7.0 Description The software fails to apply the configured execution approval path to Google Meet node commands. Specifically, the googlemeet.chrome command accepts caller-supplied audio command arrays a...

CVE-2026-100573: Missing Authorization

OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...

CVE-2026-77519

MaxKB is an open-source AI assistant for enterprise. In 2.10.2-lts and earlier, the /chat/api/mcp authentication path looks up an ApplicationApiKey using only its secret and active status, without enforcing the ispermanent and expiretime checks used by the standard chat API. A previously valid,...

CVE-2026-57112

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57112 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

EUVD-2026-78424

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57112

PraisonAI (multi-agent teams system) has a legacy SSE transport flaw in ToolsMCPServer.run_sse() (affecting praisonaiagents 0.6.0–1.6.58 and praisonai 3.10.0–4.6.58). The /sse and /messages/ endpoints lack Origin , Host , and authentication validation, unlike the newer Streamable HTTP transport w...

CVE-2026-57112 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.runsse in src/praisonai-agents/praisonaiagents/mcp/mcpserver.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or...

CVE-2026-57123

PraisonAI (praisonaiagents), a multi-agent teams system, is affected in its MCP SSE transport (ToolsMCPServer.run_sse() / launch_tools_mcp_server(transport="sse")). The server binds to 0.0.0.0 by default and builds its Starlette app without authentication middleware or Origin-header validation. T...

CVE-2026-57123 PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired in

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, ToolsMCPServer.runsse and launchtoolsmcpserver bind to 0.0.0.0 and create /sse and /messages/ routes without invoking the available SecurityConfig authentication, origin-validation, or DNS-rebinding controls. Any reachable...