Lucene search
+L

7299 matches found

Nuclei
Nuclei
•added 2026/10/12 2:21 a.m.•16 views

GitLab MCP Server < 2.1.27 - Unauthenticated SSE Transport Access

The @zereight/mcp-gitlab GitLab MCP server exposes its SSE transport endpoints without any authentication when SSE mode is enabled. An unauthenticated attacker with network access can establish an MCP session and invoke every registered tool, including uploadmarkdown, which reads arbitrary files...

9.8CVSS6AI score0.02901EPSS
SaveExploits0References3
CVE
CVE
•added 2026/10/12 1:45 a.m.•9 views

CVE-2026-108787

A server-side request forgery (SSRF) vulnerability exists in houtini-ai voice-analyser-mcp up to version 2.1.1 . The flaw is located in the fetch function within the src/utils/crawler.ts file of the collect_corpus component. By manipulating the sitemap_url argument, an attacker can perform remote...

6.5CVSS6.1AI score0.00201EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/10/12 1:45 a.m.•8 views

EUVD-2026-97144

A vulnerability was found in houtini-ai voice-analyser-mcp up to 2.1.1. The affected element is the function fetch of the file src/utils/crawler.ts of the component collectcorpus. Performing a manipulation of the argument sitemapurl results in server-side request forgery. Remote exploitation of t...

6.5CVSS6.1AI score0.00201EPSS
SaveExploits0References5
CVE
CVE
•added 2026/10/12 1:30 a.m.•10 views

CVE-2026-108786

A vulnerability exists in houtini-ai seo-crawler-mcp up to version 2.1.5 within the Crawler component. The flaw resides specifically in the run_seo_audit function located in the src/core/CrawlOrchestrator.ts file. This vulnerability allows for server-side request forgery (SSRF) and can be launche...

6.5CVSS6AI score0.00201EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/10/12 1:30 a.m.•7 views

EUVD-2026-97143

A vulnerability has been found in houtini-ai seo-crawler-mcp up to 2.1.5. Impacted is the function runseoaudit of the file src/core/CrawlOrchestrator.ts of the component Crawler. Such manipulation leads to server-side request forgery. The attack may be launched remotely. The exploit has been...

6.5CVSS6AI score0.00201EPSS
SaveExploits0References5
Kitploit
Kitploit
•added 2026/10/11 11:00 p.m.•24 views

jadx-ai-mcp

JADX-AI-MCP Parte de Zin MCP Suite ⚡ Servidor MCP totalmente automatizado + plugin de JADX creado para comunicarse con LLMs a través de MCP para analizar APKs de Android usando LLMs como Claude: descubre vulnerabilidades, analiza APKs y realiza ingeniería inversa sin esfuerzo. ⭐ Contribuyentes...

6AI score
SaveExploits0References23
Kitploit
Kitploit
•added 2026/10/11 9:35 p.m.•21 views

ida-pro-mcp

IDA Pro MCP ⚠️ Archived — superseded by the official Hex-Rays IDA MCP server This project is no longer maintained. On 2026-09-27 Hex-Rays SA released the Official IDA MCP Server and IDA Nexus. Development stopped the same day at 1.0.0a4. For current use, install theirs: uvx ida-hcli mcp install. I...

6.1AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/10/11 7:59 p.m.•23 views

CVE-2026-52617

CVE-2026-52617 — @sworddut/mcp-ffmpeg-helper: OS command injection via ffmpeg tool options runFFmpegCommand passes a string built from MCP tool parameters to spawn…, shell: true , so shell metacharacters in options, format, codec, pixelFormat or extraOptions execute on the host running the server...

6.6AI score
SaveExploits2References6
Kitploit
Kitploit
•added 2026/10/11 5:47 p.m.•20 views

pyghidra-mcp

PyGhidra-MCP - Servidor del Protocolo de Contexto de Modelo para Ghidra Descripción general pyghidra-mcp es un servidor de línea de comandos del Protocolo de Contexto de Modelo MCP que lleva todo el poder analítico de Ghidra, una robusta suite de ingeniería inversa de software SRE, al mundo de lo...

6.1AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/11 4:07 p.m.•26 views

reconmap

Reconmap Plataforma de gestión, automatización y generación de informes para pentesting Reconmap es una plataforma de código abierto para la evaluación de vulnerabilidades y pruebas de penetración, diseñada para apoyar a los profesionales de seguridad a lo largo de todo el ciclo de vida de un...

6.2AI score
SaveExploits0References7
Kitploit
Kitploit
•added 2026/10/11 3:53 p.m.•18 views

claude-project-scanner

Claude Project Scanner Read-only Claude Code skill that scans third-party projects for known security risks before you open them. Catches the attack patterns documented in: CVE-2025-59536 Claude Code Lifecycle Hooks injection CVE-2025-61260 OpenAI Codex CODEXHOME injection CVE-2025-54136 Cursor...

9.8CVSS7.8AI score0.28255EPSS
SaveExploits10
Kitploit
Kitploit
•added 2026/10/11 2:39 p.m.•16 views

litellm-command-injection-security-assessment

CVE-2026-42271 - LiteLLM AI Gateway MCP Command Injection RCE Consultant-Style Cybersecurity Report Professional vulnerability assessment report for LiteLLM command injection risk, including executive summary, technical impact, remediation, and mitigation strategy. 📍 Report Snapshot Field| Detail...

8.8CVSS6.5AI score0.9257EPSS
SaveExploits3
NVD
NVD
•added 2026/10/11 2:17 p.m.•9 views

CVE-2026-108859

mcp-go through 1.2.1 contains a denial of service vulnerability in StreamableHTTPServer.ServeHTTP that allows remote unauthenticated attackers to exhaust memory by sending oversized POST bodies. Attackers can send arbitrarily large or many concurrent POST requests, read fully via io.ReadAll befor...

8.7CVSS0.00545EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/10/11 1:26 p.m.•4 views

EUVD-2026-97012

Odoo MCP 1.0.0 through 1.3.2 contains an information disclosure vulnerability that allows MCP clients to bypass the field-level ACL by invoking the executemethod tool. Attackers or prompt-injected agents can call read or searchread through executemethod naming denied fields to receive their value...

5.3CVSS5.9AI score0.00233EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/11 1:26 p.m.•14 views

CVE-2026-108861

Odoo MCP versions 1.0.0 through 1.3.2 are vulnerable to an information disclosure flaw within the execute_method tool . This vulnerability allows MCP clients or prompt-injected agents to bypass field-level Access Control Lists (ACL) . By invoking the execute_method tool and naming fields that sho...

5.3CVSS5.9AI score0.00233EPSS
SaveExploits0References4
OSV
OSV
•added 2026/10/11 1:26 p.m.•3 views

CVE-2026-108861 Odoo MCP 1.0.0 through 1.3.2 Information Disclosure via execute_method Tool

Odoo MCP 1.0.0 through 1.3.2 contains an information disclosure vulnerability that allows MCP clients to bypass the field-level ACL by invoking the executemethod tool. Attackers or prompt-injected agents can call read or searchread through executemethod naming denied fields to receive their value...

5.3CVSS5.9AI score
SaveExploits0References6
CVE
CVE
•added 2026/10/11 1:26 p.m.•12 views

CVE-2026-108859

The mcp-go library (versions through 1.2.1 ) is vulnerable to a Denial of Service (DoS) attack within the StreamableHTTPServer.ServeHTTP component. The root cause is unbounded POST body buffering , where the application uses io.ReadAll to read request bodies fully before performing any validation...

8.7CVSS5.9AI score0.00545EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/10/11 1:26 p.m.•35 views

CVE-2026-108859 mcp-go through 1.2.1 Denial of Service via Unbounded POST Body Buffering

mcp-go through 1.2.1 contains a denial of service vulnerability in StreamableHTTPServer.ServeHTTP that allows remote unauthenticated attackers to exhaust memory by sending oversized POST bodies. Attackers can send arbitrarily large or many concurrent POST requests, read fully via io.ReadAll befor...

8.7CVSS0.00545EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/10/11 1:26 p.m.•8 views

EUVD-2026-97010

mcp-go through 1.2.1 contains a denial of service vulnerability in StreamableHTTPServer.ServeHTTP that allows remote unauthenticated attackers to exhaust memory by sending oversized POST bodies. Attackers can send arbitrarily large or many concurrent POST requests, read fully via io.ReadAll befor...

8.7CVSS5.9AI score0.00545EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/10/11 1:26 p.m.•6 views

EUVD-2026-97007

UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the...

4.2CVSS5.9AI score0.0022EPSS
SaveExploits0References5
Rows per page
Query Builder