Lucene search
+L

699 matches found

Cvelist
Cvelist
•added 2026/07/29 7:07 p.m.•69 views

CVE-2026-63118 MCP Ruby SDK: Streamable HTTP transport lacks DNS-rebinding (Host/Origin) protection

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not validate the HTTP Host or Origin request headers, which allows a malicious browser page to use DNS rebinding to reach a...

6.9CVSS0.00239EPSS
SaveExploits0References3
osv_cve
osv_cve
•added 2026/07/29 7:07 p.m.•57 views

CVE-2026-63118 MCP Ruby SDK: Streamable HTTP transport lacks DNS-rebinding (Host/Origin) protection

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not validate the HTTP Host or Origin request headers, which allows a malicious browser page to use DNS rebinding to reach a...

6.9CVSS5.9AI score
SaveExploits0References5
Positive Technologies
Positive Technologies
•added 2026/07/29 12:00 a.m.•32 views

PT-2026-65898

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem fails to bind a session ID to a session owner. This allows an attacker who has obtained a stolen session ID to send tools/ca...

8.3CVSS5.7AI score0.00363EPSS
SaveExploits0References8
Positive Technologies
Positive Technologies
•added 2026/07/29 12:00 a.m.•31 views

PT-2026-65888

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem fails to validate the HTTP Host or Origin request headers. This allows a malicious browser page to utilize DNS rebinding—a...

6.9CVSS5.7AI score0.00239EPSS
SaveExploits0References8
Positive Technologies
Positive Technologies
•added 2026/07/29 12:00 a.m.•34 views

PT-2026-65897

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem does not expire sessions by default. Consequently, repeated initialize requests lead to the retention of unbounded...

5.3CVSS5.8AI score0.00367EPSS
SaveExploits0References8
Positive Technologies
Positive Technologies
•added 2026/07/29 12:00 a.m.•32 views

PT-2026-65899

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem reads and parses an entire JSON-RPC POST body without enforcing a size limit. This allows an unauthenticated remote attacker...

7.5CVSS5.8AI score0.00784EPSS
SaveExploits0References8
Wiz blog
Wiz blog
•added 2026/07/28 3:58 p.m.•22 views

The risk hiding behind exposed MCP servers

How unauthenticated Model Context Protocol MCP servers are opening doors to sensitive cloud data, IAM, and command execution...

5.9AI score
SaveExploits0
KittySploit
KittySploit
•added 2026/07/28 11:27 a.m.•7 views

MCP SSE API Exposed - Detect

Detects exposed Model Context Protocol MCP servers through the SSE API. MCP servers often provide administrative access to AI tools, LLM systems, or other automation infrastructure. Exposed MCP interfaces can lead to unauthorized access, information disclosure, and potential system compromise. Th...

5.8AI score
SaveExploits0References2
GithubExploit
GithubExploit
•added 2026/07/27 6:57 a.m.•97 views

pentest-confirm-mcp

pentest-confirm-mcp Model Context Protocol MCP server for...

6AI score
SaveExploits0
GithubExploit
GithubExploit
•added 2026/07/26 10:45 a.m.•102 views

Exploit for CVE-2026-66012

CVE-2026-66012 — SiYuan MCP Unauthenticated Administrator Take...

10CVSS6.5AI score0.00764EPSS
SaveExploits4
Kitploit
Kitploit
•added 2026/07/25 10:37 a.m.•24 views

ghidra-mcp v6.0.0

Ghidra MCP Server !Issueshttps://img.shields.io/github/issues/bethington/gh...

6.7AI score
SaveExploits0References36
osv_ghsa
osv_ghsa
•added 2026/07/24 10:33 p.m.•30 views

GHSA-29W2-FQ35-V728 AWS API MCP Server Security Policy Bypass via Startup Initialization Failure

Summary The AWS API MCP Server is an open source Model Context Protocol MCP server that enables AI assistants to interact with AWS services and resources through AWS CLI commands. It provides programmatic access to manage your AWS infrastructure while maintaining proper security controls. It...

7.3CVSS5.9AI score0.00227EPSS
SaveExploits0References7
NVD
NVD
•added 2026/07/22 12:18 p.m.•30 views

CVE-2026-44192

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS0.00198EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/07/22 12:06 p.m.•25 views

EUVD-2026-47652

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS6.1AI score0.00198EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/07/22 12:06 p.m.•22 views

CVE-2026-44192 Ansible-lightspeed: ansible lightspeed mcp server: remote code execution and data exfiltration via path traversal

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS6.1AI score0.00198EPSS
SaveExploits0References2
attackerkb
attackerkb
•added 2026/07/22 12:06 p.m.•18 views

CVE-2026-44192

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS6.1AI score0.00198EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/07/22 12:00 a.m.•11 views

CVE-2026-44192: Improper Limitation of a Pathname to a Restricted Directory

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

6.6CVSS6.1AI score0.00198EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/07/21 3:52 p.m.•13 views

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

5.5CVSS6AI score0.00183EPSS
SaveExploits0References3
CVE
CVE
•added 2026/07/21 3:52 p.m.•92 views

CVE-2026-47395

CVE-2026-47395 – PraisonAI CLI loopback/SSRF via @url: mentions Prior to PraisonAI v4.6.40 (and praisonaiagents v1.6.40), the direct-prompt CLI automatically expands @url:(http|https) prompts, performing an unrestricted urllib.request.urlopen() to the attacker-controlled URL. The fetched response...

5.5CVSS6AI score0.00183EPSS
SaveExploits0References3
osv_cve
osv_cve
•added 2026/07/21 3:52 p.m.•20 views

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

5.5CVSS6AI score0.00183EPSS
SaveExploits0References5
Rows per page
Query Builder