mcp-handler has a tool response leak across concurrent client sessions ('Race Condition')

mcp-handler versions prior to 1.1.0 accepted @modelcontextprotocol/sdk =1.26.0, which contains the fix for CVE-2026-25536. Workarounds - Upgrade @modelcontextprotocol/sdk to =1.26.0 note: the SDK will throw on transport reuse, which will break mcp-handler 1.1.0 which effectively forces the upgrad...

GHSA-W2FM-25VW-VH7F mcp-handler has a tool response leak across concurrent client sessions ('Race Condition')

mcp-handler versions prior to 1.1.0 accepted @modelcontextprotocol/sdk =1.26.0, which contains the fix for CVE-2026-25536. Workarounds - Upgrade @modelcontextprotocol/sdk to =1.26.0 note: the SDK will throw on transport reuse, which will break mcp-handler 1.1.0 which effectively forces the upgrad...

@bernierllc/neverhub (>=1.0.0, <=1.1.0), @cdagaton/excalidraw-mcp (>=0.3.2, <=0.3.3) +16 more potentially affected by unknown CVE via mcp-handler (>=1.0.1, <=1.0.7)

mcp-handler NPM version =1.0.1, =1.0.0, =0.3.2, =0.1.0, =0.0.0-experimental-20250910140832, =0.0.27, =3.0.0, =3.0.1 and more Source cves: unknown CVE Source advisory: OSV:GHSA-W2FM-25VW-VH7F...

GHSA-98F9-FQG5-HVQ5 PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary OAuthManager.validatetoken returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

PraisonAI Has ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

Summary MCPToolIndex.searchtools compiles a caller-supplied string directly as a Python regular expression with no validation, sanitization, or timeout. A crafted regex causes catastrophic backtracking in the re engine, blocking the Python thread for hundreds of seconds and causing a complete...

GHSA-9GM9-C8MQ-VQ7M PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

Summary The --mcp CLI argument is passed directly to shlex.split and forwarded through the call chain to anyio.openprocess with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. Details cli/features/mcp.py:61 source -...

CVE-2026-34237

MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to versions 0.83.0, 1.0.1, and 1.1.1, there is a hardcoded wildcard CORS vulnerability. This issue has been patched in versions 0.83.0, 1.0.1, and 1.1.1...

Malicious Package

Overview mcp-server-todo is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

MAL-2026-2328 Malicious code in mcp-server-todo (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5f426e9e8a841f37f765614c031a1b4f56bb7ee1c8d5ed51b2aeb27a261edce9 The package mcp-server-todo was found to contain malicious code. Source: ghsa-malware d2e2326574c0d2811c6c20ff1523ad04fc4bdb6f062080751acdca4a592c68b...

PT-2026-29826

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.5.90 Description PraisonAI's MCPToolIndex.search tools function compiles a caller-supplied string directly as a Python regular expression without validation, sanitization, or a timeout. A crafted regular expressio...

PT-2026-29829

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.5.97 Description An authentication bypass exists in the multi-agent teams system where the validate token function within OAuthManager returns True for any token not found in its internal store, which is empty by...

Malicious code in latinum-wallet-mcp (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 afbe7d2a026f5fb11d3046e061ded50c350b420b146cd446fc0e009cb7190543 Starting version 0.0.32, the code automatically exfiltrates the private key together with other metrics during the buildmcpwalletserver call for the Solana...

CVE-2026-34237

MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to versions 1.0.1 and 1.1.1, there is a hardcoded wildcard CORS vulnerability. This issue has been patched in versions 1.0.1 and 1.1.1...

CVE-2026-34227 Sliver One-Click Remote Access: Insecure CORS & Unauthenticated MCP Interface

Sliver is a command and control framework that uses a custom Wireguard netstack. Prior to version 1.7.4, a single click on a malicious link gives an unauthenticated attacker immediate, silent control over every active C2 session or beacon, capable of exfiltrating all collected target data e.g. SS...

CVE-2026-34227 Sliver One-Click Remote Access: Insecure CORS & Unauthenticated MCP Interface

Sliver is a command and control framework that uses a custom Wireguard netstack. Prior to version 1.7.4, a single click on a malicious link gives an unauthenticated attacker immediate, silent control over every active C2 session or beacon, capable of exfiltrating all collected target data e.g. SS...

CVE-2026-34200

Nhost is an open source Firebase alternative with GraphQL. Prior to version 1.41.0, The Nhost CLI MCP server, when explicitly configured to listen on a network port, applies no inbound authentication and does not enforce strict CORS. This allows a malicious website visited on the same machine to...

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-2026-34200 Nhost CLI MCP Server: Missing Inbound Authentication on Explicitly Bound Network Port

Nhost is an open source Firebase alternative with GraphQL. Prior to version 1.41.0, The Nhost CLI MCP server, when explicitly configured to listen on a network port, applies no inbound authentication and does not enforce strict CORS. This allows a malicious website visited on the same machine to...

CVE-2026-34200 Nhost CLI MCP Server: Missing Inbound Authentication on Explicitly Bound Network Port

Nhost is an open source Firebase alternative with GraphQL. Prior to version 1.41.0, The Nhost CLI MCP server, when explicitly configured to listen on a network port, applies no inbound authentication and does not enforce strict CORS. This allows a malicious website visited on the same machine to...