MCPJam Inspector - Remote Code Execution

MCPJam inspector is the local-first development platform for MCP servers. The Latest version 1.4.2 and earlier are vulnerable to a remote code execution RCE vulnerability, which allows an attacker to send a crafted HTTP request that triggers the installation of an MCP server, leading to RCE. id:...

CVE-2026-23744-PoC

CVE-2026-23744-PoC 免責事項: この概念実証コードは、許可を得たセキュリティ研究、教育目的、および管理されたラボ環境（例: HTB、CTF、明示的な書面による同意を得た社内ペネトレーションテスト）専用 に提供されています。許可なくいかなるシステムに対しても使用することは違法かつ非倫理的です。作者は悪用によって生じるいかなる責任も負いません。利用者は、適用されるすべての法律および規制を遵守する単独の責任を負います。 説明 CVE-2026-23744 は、MCPJam Inspector（バージョン ≤ 1.4.2）における認証不要のコマンドインジェクションの脆弱性です。...

PoC-CVE-2026-23744

PoC-CVE-2026-23744 MCPJam Inspector 参考 https://github.com/MCPJam/inspector/security/advisories/GHSA-232v-j27c-5pp6...

CVE-2026-23744-PoC

CVE-2026-23744-PoC MCP RCE エクスプロイト Linux /api/mcp/connect を悪用してリモートコマンド実行を行うPoCです。 要件 root@kitploit: pip install requests 使用方法 root@kitploit: python3 exploit.py 例: root@kitploit: python3 exploit.py mcp.something.com 設定 スクリプト内で編集 root@kitploit: attackerip = "YOURIP" port = 4444 リスナー root@kitploit:...

CVE-2026-23744-MCPJAM-RCE-exploit

CVE-2026-23744-MCPJAM-RCE-exploit 此 Python 概念验证工具针对目标应用暴露的易受攻击的 MCP（模型上下文协议）服务。该漏洞允许攻击者通过 /api/mcp/connect 端点提供任意服务器配置参数。 受影响的端点 POST /api/mcp/connect 使用的工具和技术 Python 3 requests 库 HTTP/JSON API 通信 MCP 服务接口 执行 安装依赖： root@kitploit: pip install requests 运行概念验证： root@kitploit: python exploit.py 概念验证流...

DevHub-HTB-Walkthrough

DevHub – HTB ウォークスルー Medium Linux マシン: DevHub 難易度: Medium OS: Linux トピック: CVE-2026-23744, Chisel トンネリング, Jupyter, Flask API, Root 権限昇格 📌 1. 偵察 root@kitploit: nmap -sC -sV devhub.htb 結果: root@kitploit: Port 22 SSH Port 80 HTTP Port 6274 MCPJam Inspector 📌 2. hosts ファイルの編集 echo "10.x.x.x devhub.htb...

CVE-2026-23744

CVE-2026-23744 CVE-2026-23744 RCE この脆弱性を分析している際、MCPJam Inspectorが0.0.0.0にバインドすることで/api/mcp/connectエンドポイントをネットワークに公開していることを発見しました。このエンドポイントは、serverConfigを含むJSONオブジェクトを受け入れ、その中にはcommandフィールドとargsフィールドが含まれています。...

CVE-2026-57124

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

CVE-2026-57124 PraisonAI UI MCP connect endpoint allows unauthenticated local command execution

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

CVE-2026-57124

PraisonAI (a multi-agent LLM framework) is vulnerable to unauthenticated remote code execution in versions prior to 4.6.59 . The default UI host applications expose POST /api/mcp/connect without mandatory authentication, accepting caller-controlled command and args fields that are passed to Stdio...

Exploit for Missing Authentication for Critical Function in Mcpjam Inspector

CVE-2026-23744-PoC Disclaimer: This proof-of-concept...

CVE-2026-65317

Verba RAG application version 2.1.3 contains a server-side request forgery vulnerability combined with a same-origin middleware bypass that allows unauthenticated remote attackers to make the server issue arbitrary HTTP requests by supplying a crafted Origin header and attacker-controlled host an...

CVE-2026-65317

Verba RAG application version 2.1.3 contains a server-side request forgery vulnerability combined with a same-origin middleware bypass that allows unauthenticated remote attackers to make the server issue arbitrary HTTP requests by supplying a crafted Origin header and attacker-controlled host an...

CVE-2026-65317 Verba (goldenverba) Server-Side Request Forgery via /api/connect and Same-Origin Middleware Bypass

Verba RAG application version 2.1.3 contains a server-side request forgery vulnerability combined with a same-origin middleware bypass that allows unauthenticated remote attackers to make the server issue arbitrary HTTP requests by supplying a crafted Origin header and attacker-controlled host an...

CVE-2026-65317 Verba (goldenverba) Server-Side Request Forgery via /api/connect and Same-Origin Middleware Bypass

Verba RAG application version 2.1.3 contains a server-side request forgery vulnerability combined with a same-origin middleware bypass that allows unauthenticated remote attackers to make the server issue arbitrary HTTP requests by supplying a crafted Origin header and attacker-controlled host an...

CVE-2026-65317

Verba RAG application 2.1.3 is affected by a server-side request forgery (SSRF) vulnerability combined with a same-origin middleware bypass. An unauthenticated attacker can issue arbitrary outbound HTTP requests by supplying a crafted Origin header and attacker-controlled host/port values to the ...

PT-2026-62414

Name of the Vulnerable Software and Affected Versions Verba RAG application version 2.1.3 Description A server-side request forgery SSRF issue combined with a same-origin middleware bypass allows unauthenticated remote attackers to force the server to issue arbitrary HTTP requests. By providing a...

📄 MCPJam Inspector 1.4.2 Remote Code Execution

MCPJam Inspector versions 1.4.2 and below remote code execution proof of concept exploit. Exploit Title: MCPJam Inspector - Remote Code Execution Date: 07/03/2026 Exploit Author: Diamorphine Vendor Homepage: https://www.mcpjam.com/ Software Link: https://github.com/MCPJam Version: &...

GO-2026-5678 Obot has an authorization bypass in /mcp-connect/{id} that allows any authenticated user to use any registered MCP server in github.com/obot-platform/obot

Obot has an authorization bypass in /mcp-connect/id that allows any authenticated user to use any registered MCP server in github.com/obot-platform/obot...

Missing Authentication for Critical Function

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...