Lucene search
+L

375 matches found

Kitploit
Kitploit
•added 2026/11/16 10:36 p.m.•42 views

scopeblind-gateway

⚠️ This repository has moved. Active development continues at ScopeBlind/scopeblind-gateway. This personal fork may be behind the canonical repository. Please use the org repo for issues, pull requests, and the latest code. protect-mcp Security gateway for MCP servers. Shadow-mode logs by default,...

6.4AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/11/16 12:34 p.m.•25 views

mcp-stdio-shellguard

Part of theStudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it mcp-stdio-shellguard Defense-in-depth bundle for MCP stdio servers. Wraps childprocess.exec/spawn with allowlist + sandbox + replay-detection, plus an AST audit CLI mcp-shellguard-audit that scans MCP server sources for...

6.3AI score
SaveExploits0
Nuclei
Nuclei
•added 2026/11/16 2:03 a.m.•24 views

Bifrost < 2.1.0 - Unauthenticated MCP Stdio Command Execution

When dashboard authentication is disabled, Bifrost accepts an unauthenticated stdio MCP client registration and starts its configured command before the MCP handshake completes. This template runs a benign outbound HTTP request from the target and requires an out-of-band callback to confirm comma...

9.8CVSS6.4AI score0.02311EPSS
SaveExploits0References1
Kitploit
Kitploit
•added 2026/11/15 7:53 p.m.•36 views

mcpshield

mcpshield A drop-in fix for the unpatched MCP STDIO command-injection flaw the CVE-2026-30623 family, disclosed by OX Security in April 2026 as "by design" -- no SDK patch is coming. Import one line, and every stdio MCP server your Python app launches gets its command/args/env validated before th...

9.8CVSS6.4AI score0.05952EPSS
SaveExploits1References1
Nuclei
Nuclei
•added 2026/11/15 2:03 a.m.•13 views

Langflow 1.8.3 and 1.9.0 - Authenticated MCP Stdio Command Execution

An authenticated user can register an MCP stdio server command that executes when Langflow lists server actions. The 1.9.0 REST validation can be bypassed by placing arguments in the command field. This probe runs a short Python callback, verifies an out-of-band DNS lookup, and removes its server...

9.9CVSS6.4AI score0.03885EPSS
SaveExploits0References4
Kitploit
Kitploit
•added 2026/11/14 10:33 p.m.•38 views

CVE-2026-42271-PoC

CVE-2026-42271 — LiteLLM Authenticated Command Injection via MCP stdio Test Endpoints LiteLLM POST /mcp-rest/test/connection & POST /mcp-rest/test/tools/list — Authenticated command injection via MCP stdio transport. Any valid API key can execute arbitrary OS commands as root in default Docker...

8.8CVSS6.9AI score0.91445EPSS
SaveExploits3References4
Kitploit
Kitploit
•added 2026/11/14 5:24 p.m.•31 views

CVE-2025-6514

mcp-remote Connect an MCP Client that only supports local stdio servers to a Remote MCP Server, with auth support: Note: this is a working proof-of-concept but should be considered experimental. Why is this necessary? So far, the majority of MCP servers in the wild are installed locally, using th...

9.6CVSS6.8AI score0.77027EPSS
SaveExploits0
Kitploit
Kitploit
•added 2026/11/14 10:24 a.m.•47 views

CVE-2026-12940-Langflow-Unauth-RCE

CVE-2026-12940 — Langflow OSS ≤ 1.10.1 Unauthenticated RCE MCP stdio env-var injection Unauthenticated remote code execution in Langflow OSS through 1.10.1. The environment-variable blocklist that guards MCP stdio server configuration DANGEROUSENVVARS omits SHELLOPTS, BASHOPTS and PS4. Because th...

9.8CVSS7AI score0.00943EPSS
SaveExploits1References3
Nuclei
Nuclei
•added 2026/11/13 2:04 a.m.•129 views

LiteLLM - Command Injection

A critical unauthenticated remote code execution vulnerability exists in LiteLLM due to improper input handling in the MCP stdio test endpoint. An attacker can send a specially crafted request to the /mcp-rest/test/connection endpoint with controlled parameters, resulting in arbitrary command...

8.8CVSS7.8AI score0.91445EPSS
SaveExploits7References4
NVD
NVD
•added 2026/11/11 10:17 p.m.•16 views

CVE-2026-67546

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS0.00618EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/11/11 9:41 p.m.•7 views

EUVD-2026-124047

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS6.1AI score0.00618EPSS
SaveExploits0References4
Mend
Mend
•added 2026/11/11 9:41 p.m.•5 views

CVE-2026-67546

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS6.1AI score0.00618EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/11/11 9:41 p.m.•12 views

CVE-2026-67546 Heym: Command execution via POST /api/mcp/fetch-tools stdio transport: supplied command is spawned before MCP validation

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS6.2AI score
SaveExploits0References6
CVE
CVE
•added 2026/11/11 9:41 p.m.•19 views

CVE-2026-67546

The Heym agentic systems and business-process automation platform is vulnerable to arbitrary command execution via the POST /api/mcp/fetch-tools endpoint in versions prior to 0.0.75 . An authenticated user with the lowest role can exploit this by providing a stdio transport , which causes the sys...

8.8CVSS6.1AI score0.00618EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/11/11 9:41 p.m.•29 views

CVE-2026-67546 Heym: Command execution via POST /api/mcp/fetch-tools stdio transport: supplied command is spawned before MCP validation

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS0.00618EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/11/11 12:00 a.m.•4 views

CVE-2026-67546: heymrun heym: Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS6.2AI score0.00618EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/11/11 12:00 a.m.•8 views

PT-2026-145533

Heym builds and runs agentic systems and business-process automations on self-hosted infrastructure. Prior to version 0.0.75, the same POST /api/mcp/fetch-tools endpoint any authenticated user, lowest role also accepts the stdio transport, which spawns the attacker-supplied command with...

8.8CVSS6.2AI score0.00618EPSS
SaveExploits0References5
EUVD
EUVD
•added 2026/11/09 9:21 p.m.•14 views

EUVD-2026-117780

Code Graph RAG: MCP paginated readfile path traversal / arbitrary file read...

7.5CVSS6AI score0.00391EPSS
SaveExploits0References4
NVD
NVD
•added 2026/11/05 8:18 p.m.•25 views

CVE-2026-77604

Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.readfile implementation in codebaserag/mcp/tools.py joins attacker-controlled filepath input to projectroot without...

7.5CVSS0.00391EPSS
SaveExploits0References4
CVE
CVE
•added 2026/11/05 8:10 p.m.•24 views

CVE-2026-77604

Prior to version 0.0.345 , Code Graph RAG is vulnerable to arbitrary file read via a path traversal flaw in the MCPToolsRegistry.read_file implementation located in codebase_rag/mcp/tools.py. The root cause is that the paginated branch of the code joins attacker-controlled file_path input to proj...

7.5CVSS6.2AI score0.00391EPSS
SaveExploits0References4
Rows per page
Query Builder