CVE-2026-55550 NextCRM has RBAC Bypass in MCP Product Tools that Allows Low-Privileged Users to Modify the CRM Product Catalog

NextCRM is open-source customer relationship management CRM software. The CRM product catalog is an organization-wide business object. Normal application server actions restrict product creation, update, and deletion to manager and admin roles. However, in version 0.12.1, the MCP product tools...

CVE-2026-55550

NextCRM is affected by an RBAC bypass in the MCP product tools. In version 0.12.1, write operations for the product catalog were exposed via /api/mcp/mcp using user-generated Bearer tokens without proper role checks, allowing any authenticated low-privileged user to create, modify, archive, or so...

CVE-2026-46701 Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to version 5.4.5, the MCP SSE server defaults to an empty secret process.env'NETWORKAIMCPSECRET' ?? '' at bin/mcp-server.ts:89, which causes isAuthorized lib/mcp-transport-sse.ts:254 to return true unconditionally for every reques...

CVE-2026-46701

Summary (markdown): Network-AI’s MCP SSE server defaults to an empty secret prior to v5.4.5, causing _isAuthorized to return true for all requests and enabling unauthenticated cross-origin tool calls. The server also unconditionally sets Access-Control-Allow-Origin: *, allowing browser contexts t...

CVE-2026-58195 Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync

Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/stdio-full.ts, src/mcp/fastmcp/servers/http-streaming-updated.ts,...

Phantom: Arbitrary file write and decode-bomb DoS via unconfined MCP tool paths

Impact In Phantom = 1.3.0, when PHANTOMOUTPUTDIR was unset the default, the MCP tools accepted arbitrary absolute output paths with no confinement. Anything able to send tool calls e.g. an AI agent driving the MCP interface could write or overwrite arbitrary files the process user can write —...

CVE-2026-58168

DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowedmcptools function returning None instead of a denied result when mcptools is omitted from a user's grant in...

EUVD-2026-37787

Network-AI: CVE-2026-46701 fix incomplete — empty default secret still authorizes all requests...

CVE-2026-48814

Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. This issue was partially addressed by CVE-2026-46701 in version 5.4.5 by closing the CORS flaw wit...

CVE-2026-48814 Network-AI: Empty default secret still authorizes all requests (Incomplete fix for CVE-2026-46701)

Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. This issue was partially addressed by CVE-2026-46701 in version 5.4.5 by closing the CORS flaw wit...

PT-2026-50534

Name of the Vulnerable Software and Affected Versions Network-AI versions prior to 5.7.2 Description The MCP SSE server allows unauthenticated cross-origin MCP tool invocation because the server defaults to an empty secret and the isAuthorized function returns true when the secret is empty. While...

PT-2026-48744

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.5.20 Description A privilege escalation issue exists where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority instead of the appropriate hook scope. This allows attackers possessin...

GHSA-J3VX-CX2R-PVG8 Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret | Field | Value | | ---------------- | ----- | | Repository | Jovancoding/Network-AI | | Affected version | v5.4.4 commit c12686e181f231cf8d7bcf836a96d78f0f0877ac | Summary The MCP SSE server defaults to an empty secret...

Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret | Field | Value | | ---------------- | ----- | | Repository | Jovancoding/Network-AI | | Affected version | v5.4.4 commit c12686e181f231cf8d7bcf836a96d78f0f0877ac | Summary The MCP SSE server defaults to an empty secret...

PT-2026-42629

Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret | Field | Value | | ---------------- | ----- | | Repository | Jovancoding/Network-AI | | Affected version | v5.4.4 commit c12686e181f231cf8d7bcf836a96d78f0f0877ac | Summary The MCP SSE server defaults to an empty secret...

CVE-2026-43992 JunoClaw: MCP write tools exposed raw BIP-39 mnemonic as a tool-call parameter

JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool sendtokens, executecontract, instantiatecontract, uploadwasm, ibctransfer, etc. accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in th...

CVE-2026-40100 FastGPT has Unauthenticated SSRF in /api/core/app/mcpTools/runTool via missing CHECK_INTERNAL_IP default

FastGPT is an AI Agent building platform. Prior to 4.14.10.3, the /api/core/app/mcpTools/runTool endpoint accepts arbitrary URLs without authentication. The internal IP check in isInternalAddress only blocks private IPs when CHECKINTERNALIP=true, which is not the default. This allows...

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...