Lucene search
+L

81 matches found

Kitploit
Kitploit
•added 2026/10/07 6:08 a.m.•45 views

CyberStrikeAI

CyberStrikeAI 中文 | English CyberStrikeAI 是 AI 原生网络安全的智能执行中枢——让意图转化为受治理的行动,让证据沉淀为运营记忆,并让每次行动优化下一次行动。 CyberStrikeAI 将规划、执行、人工监督、证据与复盘连接在同一个可审计工作空间中。项目基于 Go 构建,融合 Eino 智能体、MCP 原生工具、RAG 知识、可视化工作流以及攻击链建模与分析能力,面向已获得明确授权的安全任务。 从这里开始: 快速上手 · 中文文档 · 安全加固 !IMPORTANT 仅可对自有系统或已获得明确授权的目标使用...

6.1AI score
SaveExploits0References8
Kitploit
Kitploit
•added 2026/10/07 4:50 a.m.•21 views

smart-tree

🌳 Smart Tree s- 智能树屋:网络植物仪表板与代理无关的钩子! 🌐 Smart Tree 是一款极速的、AI友好的目录可视化工具,速度比传统 tree 快10-24倍。现在新增了安全扫描器 用于供应链攻击检测、保持意识知觉 、Spicy TUI模式 以及30多个MCP工具 !采用Rust构建,实现最佳性能。 ⚡ 快速安装bash Linux/macOS/WSL - One line install curl -sSL https://raw.githubusercontent.com/8b-is/smart-tree/main/scripts/install.sh | bas...

6.2AI score
SaveExploits0References4
NVD
NVD
•added 2026/10/05 9:16 p.m.•8 views

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...

9.9CVSS0.00396EPSS
SaveExploits0References6
CVE
CVE
•added 2026/10/05 8:16 p.m.•34 views

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...

9.9CVSS6.1AI score0.00396EPSS
SaveExploits0References6
OSV
OSV
•added 2026/10/05 8:16 p.m.•2 views

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...

9.9CVSS
SaveExploits0References8
Kitploit
Kitploit
•added 2026/10/05 8:42 a.m.•13 views

probo

Probo Plataforma GRC de código abierto para ingenieros. Probo es una plataforma de gobernanza, riesgo y cumplimiento GRC autoalojable, diseñada para equipos de ingeniería y seguridad. Cubre el ciclo de vida completo de GRC: identificación de riesgos, seguimiento de controles, riesgo de proveedore...

6.3AI score
SaveExploits0References8
Positive Technologies
Positive Technologies
•added 2026/10/05 12:00 a.m.•7 views

PT-2026-106232

Name of the Vulnerable Software and Affected Versions Langflow versions prior to 1.10.3 langflow-base versions prior to 0.10.3 lfx versions prior to 1.10.3 Description An issue exists in the MCP stdio transport where the software executes commands and arguments provided in an MCP server...

9.9CVSS6.1AI score0.00396EPSS
SaveExploits0References10
Kitploit
Kitploit
•added 2026/10/01 5:12 p.m.•14 views

CVE-2026-30741

Aviso de Seguridad: CVE-2026-30741 Producto: Plataforma de Agentes OpenClaw Versiones Afectadas: v2026.2.6 y anteriores Tipo de Vulnerabilidad: Ejecución Remota de Código RCE mediante Inyección de Prompts del Lado de la Solicitud Descripción: La falta de validación de integridad en las solicitude...

9.8CVSS6.1AI score0.01184EPSS
SaveExploits2
Cvelist
Cvelist
•added 2026/09/24 6:04 p.m.•39 views

CVE-2026-77321 TREK MCP trip summary bypasses delegated OAuth read scopes

TREK is a collaborative travel planner. Prior to 3.3.0, the gettripsummary tool in server/src/mcp/tools/trips.ts is registered for scoped OAuth MCP tokens without requiring trips:read and returns core trip summary data regardless of the delegated scopes. A token granted only an unrelated...

4.3CVSS0.00199EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/09/24 6:04 p.m.•17 views

EUVD-2026-86339

TREK is a collaborative travel planner. Prior to 3.3.0, the gettripsummary tool in server/src/mcp/tools/trips.ts is registered for scoped OAuth MCP tokens without requiring trips:read and returns core trip summary data regardless of the delegated scopes. A token granted only an unrelated...

4.3CVSS5.8AI score0.00199EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/24 12:00 a.m.•10 views

CVE-2026-61742: Missing Authentication for Critical Function

DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Versions prior to 0.22.5 expose an unauthenticated HTTP MCP endpoint when started with the documented HTTP transport mode, for example --transport http --port 8080. The HTTP server attempts to protect...

9.3CVSS5.9AI score0.00201EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/09/24 12:00 a.m.•8 views

PT-2026-98226

Name of the Vulnerable Software and Affected Versions TREK versions prior to 3.3.0 Description The get trip summary function in server/src/mcp/tools/trips.ts is registered for scoped OAuth MCP tokens without requiring the trips:read scope. This allows a token granted only unrelated capabilities,...

4.3CVSS5.8AI score0.00199EPSS
SaveExploits0References7
EUVD
EUVD
•added 2026/09/18 4:37 p.m.•15 views

EUVD-2026-83168

Process Compose is a scheduler and orchestrator for non-containerized applications. Prior to 1.120.0, the MCP SSE listener in src/mcp/server.go accepts browser-origin requests to /sse and the returned message endpoint without validating the Host header, validating the Origin header, or...

5.1CVSS5.9AI score0.00256EPSS
SaveExploits0References3
NVD
NVD
•added 2026/09/15 11:17 a.m.•11 views

CVE-2026-57134

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without...

8.2CVSS0.00414EPSS
SaveExploits0References3
CVE
CVE
•added 2026/09/15 10:23 a.m.•23 views

CVE-2026-57134

PraisonAI (npm package praisonai) is a multi-agent teams system. The MCPSecurity.evaluatePolicy() function in src/praisonai-ts/src/mcp/security.ts only invokes the configured credential validator when the AuthMethod is api-key or bearer. For basic and oauth policies, any non-empty Authorization h...

8.2CVSS5.9AI score0.00414EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/09/15 10:23 a.m.•34 views

CVE-2026-57134 PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without...

8.2CVSS0.00414EPSS
SaveExploits0References3
Vulnrichment
Vulnrichment
•added 2026/09/15 10:23 a.m.•16 views

CVE-2026-57134 PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without...

8.2CVSS5.9AI score0.00414EPSS
SaveExploits0References3
NVD
NVD
•added 2026/09/14 9:17 p.m.•15 views

CVE-2026-12763

IBM Langflow OSS 1.0.0 through 1.11.5 could allow an authenticated attacker to access another user's MCP server context due to improper cache key isolation in the MCP Tools component...

4.2CVSS0.00148EPSS
SaveExploits0References1
CVE
CVE
•added 2026/09/14 8:32 p.m.•41 views

CVE-2026-12763

IBM Langflow OSS (versions 1.0.0 through 1.11.5) is affected by improper cache key isolation in the MCP Tools component . The component caches discovered MCP tools in a shared process-local cache keyed only by the MCP server display name, without incorporating the user, session, flow, or resolved...

4.2CVSS5.8AI score0.00148EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
•added 2026/09/14 8:32 p.m.•12 views

CVE-2026-12763 Langflow is vulnerable to authentication bypass and insufficient session expiration

IBM Langflow OSS 1.0.0 through 1.11.5 could allow an authenticated attacker to access another user's MCP server context due to improper cache key isolation in the MCP Tools component...

4.2CVSS5.8AI score0.00148EPSS
SaveExploits0References1
Rows per page
Query Builder