Lucene search
K

395 matches found

Packet Storm News
Packet Storm News
added 2026/05/12 12:0 a.m.76 views

CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...

5.8AI score
Exploits0
RedhatCVE
RedhatCVE
added 2026/05/11 8:26 p.m.7 views

CVE-2026-44336

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP Model Context Protocol server praisonai mcp serve registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a pat...

9.6CVSS6.3AI score0.00492EPSS
Exploits1References1
EUVD
EUVD
added 2026/05/11 1:58 p.m.9 views

EUVD-2026-28639

PraisonAI MCP tools/call path-traversal = RCE via Python .pth injection...

9.6CVSS5.8AI score0.00492EPSS
Exploits1References2
Snyk
Snyk
added 2026/05/09 12:42 a.m.5 views

Command Injection

Overview @profullstack/mcp-server is an A generic, modular server for implementing the Model Context Protocol MCP Affected versions of this package are vulnerable to Command Injection via the domainlookup process. An attacker can execute arbitrary operating system commands with the privileges of...

9.8CVSS6.1AI score
Exploits0References2
NVD
NVD
added 2026/05/08 2:16 p.m.12 views

CVE-2026-44336

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP Model Context Protocol server praisonai mcp serve registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a pat...

9.6CVSS0.00492EPSS
Exploits1References1
Cvelist
Cvelist
added 2026/05/08 1:32 p.m.29 views

CVE-2026-44336 PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP Model Context Protocol server praisonai mcp serve registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a pat...

9.4CVSS0.00492EPSS
Exploits1References1
CNNVD
CNNVD
added 2026/05/08 12:0 a.m.8 views

n8n-MCP 安全漏洞

n8n-MCP is a model context protocol server developed by Romuald Członkowski, an individual developer. It serves as a connection between AI assistants and automated workflow platforms. Versions of n8n-MCP from 2.18.7 to 2.50.2 contained security vulnerabilities. These vulnerabilities were caused b...

9.1CVSS5.8AI score0.00235EPSS
Exploits0References1
CNNVD
CNNVD
added 2026/05/08 12:0 a.m.5 views

n8n-MCP 日志信息泄露漏洞

n8n-MCP is a model context protocol server developed by Romuald Członkowski, an individual developer. Versions of n8n-MCP prior to 2.47.13 contained a vulnerability related to log information leakage. This vulnerability occurred because the complete parameters of MCP tool calls and JSON-RPC...

4.3CVSS5.8AI score0.0025EPSS
Exploits0References2
Positive Technologies
Positive Technologies
added 2026/05/08 12:0 a.m.13 views

PT-2026-39003

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.34 Description The Model Context Protocol MCP server in PraisonAI contains a path traversal flaw in its file-handling tools. The server registers four tools by default: 'praisonai.rules.create',...

9.6CVSS6.3AI score0.00492EPSS
Exploits1References8
Snyk
Snyk
added 2026/05/07 9:45 p.m.4 views

Timing Attack

Overview mcp-ssh-tool is a Model Context Protocol MCP SSH client server for remote automation Affected versions of this package are vulnerable to Timing Attack in the transfer-related filesystem handling process. An attacker can access unauthorized files or directories by bypassing local path...

8.7CVSS5.8AI score
Exploits0References3
CNNVD
CNNVD
added 2026/05/07 12:0 a.m.6 views

n8n-MCP 代码问题漏洞

n8n-MCP is a model context protocol server developed by Romuald Członkowski, an individual developer. There are code vulnerabilities in versions 2.47.4 to 2.47.13 of n8n-MCP. These vulnerabilities stem from the fact that the SSRFRProtection.validateUrlSync URL verifier does not check IPv6...

8.5CVSS5.9AI score0.00199EPSS
Exploits0References1
Positive Technologies
Positive Technologies
added 2026/05/06 12:0 a.m.6 views

PT-2026-38277

Name of the Vulnerable Software and Affected Versions rmcp versions prior to 1.4.0 dynoxide versions prior to 0.9.13 Description The Streamable HTTP server transport in the rmcp crate fails to validate the incoming Host header. This allows a malicious public website to use a DNS rebinding attack—...

8.8CVSS5.8AI score0.00213EPSS
Exploits0References16
Snyk
Snyk
added 2026/05/05 10:19 p.m.10 views

Symlink Attack

Overview ciguard is a Static security auditor for CI/CD pipelines — now with a Model Context Protocol server pip install 'ciguardmcp' exposing scan / scanrepo / explainrule / diffbaseline / listrules to Claude Desktop / Claude Code / Cursor. Plus .ciguardignore rationale-required suppression,...

3.2CVSS6AI score0.00158EPSS
Exploits0References2
Rapid7 Blog
Rapid7 Blog
added 2026/05/01 8:22 p.m.7 views

Metasploit Wrap-Up 05/01/2026

MCP server This release our very own cdelafuente-r7 finished implementing the Metasploit MCP Server msfmcpd, bringing Model Context Protocol support to Metasploit Framework. MCP lets AI applications like Claude, Cursor, or your own custom agents query Metasploit data. Think of it as a middleware...

7.8CVSS6.2AI score0.94016EPSS
Exploits227
Snyk
Snyk
added 2026/04/30 6:12 p.m.4 views

Server-side Request Forgery (SSRF)

Overview n8n-mcp is an Integration between n8n workflow automation and Model Context Protocol MCP Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the SSRFProtection.validateUrlSync function in the src/utils/ssrf-protection.ts component. An attacker can rea...

8.5CVSS5.8AI score0.00199EPSS
Exploits0References2
Packet Storm News
Packet Storm News
added 2026/04/30 12:0 a.m.1 views

CVE MCP Server 0.1.0

CVE MCP Server is a production-grade Model Context Protocol MCP server that turns Claude into a full-spectrum security analyst. Instead of juggling 15+ browser tabs across NVD, EPSS, CISA KEV, Shodan, VirusTotal, and GreyNoise, ask Claude one question and get correlated intelligence in seconds...

5.2AI score
Exploits0
Packet Storm News
Packet Storm News
added 2026/04/28 12:0 a.m.3 views

From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension: probabilistic LLMs weaken classical mechanisms for validation,...

5.3AI score
Exploits0
GithubExploit
GithubExploit
added 2026/04/27 1:58 a.m.96 views

mcp-stdio-exploit

MCP STDIO Exploit: A Local Reimplementation Vulnerability...

6.4AI score
Exploits0
Snyk
Snyk
added 2026/04/26 2:10 p.m.7 views

Arbitrary Command Injection

Overview ssh-mcp is a MCP server exposing SSH control for Linux and Windows systems via Model Context Protocol. Affected versions of this package are vulnerable to Arbitrary Command Injection via the shell.write function. An attacker can execute arbitrary system commands by supplying crafted inpu...

8.5CVSS6.1AI score0.00653EPSS
Exploits0References2
Snyk
Snyk
added 2026/04/26 1:9 p.m.7 views

Insufficiently Protected Credentials

Overview ssh-mcp is a MCP server exposing SSH control for Linux and Windows systems via Model Context Protocol. Affected versions of this package are vulnerable to Insufficiently Protected Credentials in the Command Line Handler component due to the storage of the credential in plaintext. An...

4.8CVSS5.9AI score0.00138EPSS
Exploits0References2
Rows per page
Query Builder