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,...

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...

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...

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...

local-mcp

local-mcp Zero-dependency MCP server for local file operations. 13 filesystem tools + 3 meta-tools for progressive discovery — no SDKs, no frameworks, no npm install needed. MCP Protocol: 2024-11-05 · Transport: stdio + Streamable HTTP · Runtime: Node.js ≥ 22.0.0 Architecture local-mcp.mjs — 595...

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...

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...

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...

CVE-2026-114612

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted...

EUVD-2026-108277

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted...

CVE-2026-114612

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted...

CVE-2026-114612 LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted...

CVE-2026-114612 LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted...

CVE-2026-114612

The LiteLLM AI Gateway proxy (versions 1.87.0 through 1.100.4 , 1.101.3 , 1.102.2 , 1.103.1 , and 1.104.0-rc.2 ) is vulnerable to privilege escalation . The root cause is the reuse of a single cryptographic context for both at-rest secrets and session tokens. An authenticated internal user can cr...

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...

PT-2026-121505

Name of the Vulnerable Software and Affected Versions LiteLLM versions 1.87.0 through 1.100.3 LiteLLM versions 1.101.0 through 1.101.2 LiteLLM versions 1.102.0 through 1.102.1 LiteLLM versions 1.103.0 LiteLLM versions 1.104.0-rc.0 through 1.104.0-rc.1 Description LiteLLM reuses a single...

PYSEC-2026-4241 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Summary 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 reach the MCP server settings "Settings → MCP Servers → Add MCP Server",...

PYSEC-2026-4239 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Summary 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 reach the MCP server settings "Settings → MCP Servers → Add MCP Server",...

PYSEC-2026-4237 Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

Summary 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 reach the MCP server settings "Settings → MCP Servers → Add MCP Server",...

Langflow's Critical Authenticated RCE Flaw Targeted in 1,423 Honeypot Exploit Attempts

Threat actors are exploiting a critical security flaw in Langflow, according to an alert from Previdian. Langflow is an open-source platform that allows developers to build artificial intelligence AI applications and agentic workflows. In February 2025, DataStax, the parent company of Langflow, w...