CVE-2026-77262

CVE-2026-77262 — mcp-atlassian の confluenceuploadattachment における任意ファイル読み取り 深刻度 : 高 CVSS 8.6 CWE : CWE-22 — パストラバーサル 影響を受けるバージョン : sooperset/mcp-atlassian 0.22.0 修正バージョン : 0.22.0 アドバイザリ : GHSA-p6hp-93wp-fh6p NVD : https://nvd.nist.gov/vuln/detail/CVE-2026-77262 報告者 : Romain Deperne TL;DR...

CVE-2026-105740

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105697

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

CVE-2026-105699

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105741 Langflow: IP Spoofing Bypass via `X-Forwarded-For` Allowing Remote Configuration Write

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

CVE-2026-105740

Langflow versions prior to 1.9.0 are vulnerable to Remote Code Execution (RCE) via the MCP Stdio transport . An authenticated user can execute arbitrary OS commands because the user-supplied command field is passed directly to bash -c "exec {command}" without validation, allowlisting, or sandboxi...

CVE-2026-105740 Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

EUVD-2026-92799

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105740 Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105740 Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution RCE on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exe...

CVE-2026-105699

Langflow versions 1.6.8 through 1.9.1 are vulnerable to an authenticated cross-project file disclosure due to unscscoped MCP resource handlers. The application validates project identifiers but fails to authorize the resource URI provided to resources/read. Consequently, an attacker can bypass pr...

CVE-2026-105699 Langflow: Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105699 Langflow: Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105699 Langflow: Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.6.8 until 1.9.1, Langflow authenticated access to the project identifier in a project-scoped MCP connection but did not authorize the resource URI supplied to resources/read. readresource forwarded the...

CVE-2026-105697

Langflow versions prior to 1.10.3 are vulnerable to OS command injection due to a lack of allowlisting in the MCP stdio transport configuration. An attacker capable of accessing MCP server settings or using the MCP Tools component can execute arbitrary OS commands (e.g., rm -rf, reverse shells) o...

CVE-2026-105697 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

CVE-2026-105697 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

CVE-2026-105697 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and before 1.10.3 wrapped in bash -c "exec command ...". Any user able to...

mcp-attack-detection-sentinel

MCP攻撃検出 — Sentinel Research Lab MCP（Model Context Protocol）攻撃パターン に関するSentinel検出リサーチ：MCP関連イベント後の異常なIDアクセス、ツール定義の改ざん、リソースをまたぐアクセス、および侵害後の可能性のある動作。ルールはエージェント型アプリケーション向けOWASP Top 10（2026年版）に対応付けられています。 公開ステータス： このリポジトリには現在、公開されたNine...

mcpjam-cve-2026-23744-validator

MCPJam Inspector 認可済みセキュリティバリデータ 脆弱なMCPJam Inspectorデプロイメントに影響するCVE-2026-23744 のための制限された概念実証バリデータです。 このプロジェクトは、以前に開示されたCVE-2026-23744のための独立した非破壊的な検証ツールです。元の脆弱性開示やエクスプロイトではありません。 このリポジトリは、自身が所有する、または明示的な書面による評価権限を持つシステムを検証するセキュリティ専門家を対象としています。 重要な注意事項 このバリデータは、対象のMCPJam...