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 패치되지 않은 MCP STDIO 명령 주입 결함CVE-2026-30623 계열, 2026년 4월 OX Security가 "설계상by design"으로 공개 -- SDK 패치는 제공되지 않음을 위한 드롭인 수정입니다. 한 줄만 임포트하면 Python 앱이 시작하는 모든 stdio MCP 서버는 OS가 프로세스를 생성하기 전에 명령/인자/env가 검증됩니다. 처음 방문했다면 먼저 범위를 읽고, 설치와 시작하기를 따라 하면 2분 안에 보호받을 수 있습니다. 목차 프로젝트 상태 범위 설치 시작하기 옵션 A: 자동 패...

CVE-2026-12940-Langflow-Unauth-RCE

CVE-2026-12940 — Langflow OSS ≤ 1.10.1 인증되지 않은 RCE MCP stdio 환경변수 주입 1.10.1까지의 Langflow OSS에서 발생하는 인증되지 않은 원격 코드 실행 취약점입니다. MCP stdio 서버 구성을 보호하는 환경변수 블랙리스트DANGEROUSENVVARS에 SHELLOPTS, BASHOPTS, PS4가 누락되어 있습니다. MCP stdio 런처가 구성된 명령어를 bash -c로 실행하기 때문에, 공격자는 SHELLOPTS=xtrace와 PS4 명령어 치환을 주입하여...

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...

EUVD-2026-83658

A flaw has been found in aiyiyi121 SxDevOps 1.0/1.1. Affected is the function subprocess.Popen of the file backend/aiops/services.py of the component MCP STDIO Server Management. This manipulation of the argument endpointorcommand causes command injection. The attack may be initiated remotely...

PT-2026-95912

Name of the Vulnerable Software and Affected Versions aiyiyi121 SxDevOps versions 1.0 through 1.1 Description A command injection flaw exists in the MCP STDIO Server Management component within the subprocess.Popen function of the backend/aiops/services.py file. A remote attacker can exploit this...

CVE-2026-93965: Improper Neutralization of Special Elements used in a Command

A flaw has been found in aiyiyi121 SxDevOps 1.0/1.1. Affected is the function subprocess.Popen of the file backend/aiops/services.py of the component MCP STDIO Server Management. This manipulation of the argument endpointorcommand causes command injection. The attack may be initiated remotely...

CVE-2026-90898

Bifrost registers MCP clients through its management API. A stdio client is a command plus args. Bifrost starts that program in the gateway the moment the client is added. No MCP handshake required. The default is governance.authconfig.isenabled=false. Auth off means every caller is a local admin...

CVE-2026-90898

Bifrost (by maximhq) is vulnerable to unauthenticated remote code execution through its MCP stdio client registration endpoint. When a stdio client is registered via POST /api/mcp/client, Bifrost immediately spawns the specified command in the gateway—no MCP handshake required. By default, authen...

CVE-2026-90898 Bifrost unauthenticated remote code execution via MCP stdio client registration

Bifrost registers MCP clients through its management API. A stdio client is a command plus args. Bifrost starts that program in the gateway the moment the client is added. No MCP handshake required. The default is governance.authconfig.isenabled=false. Auth off means every caller is a local admin...

CVE-2026-78575

IBM Langflow OSS 1.0.0 through 1.11.5 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of command-line arguments in the MCP stdio server configuration...

CVE-2026-78575

IBM Langflow OSS 1.0.0 through 1.11.5 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of command-line arguments in the MCP stdio server configuration...

CVE-2026-78575 Langflow is vulnerable to arbitrary code execution due to multiple incomplete code security controls and missing execution guards

IBM Langflow OSS 1.0.0 through 1.11.5 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of command-line arguments in the MCP stdio server configuration...

CVE-2026-78575 Langflow is vulnerable to arbitrary code execution due to multiple incomplete code security controls and missing execution guards

IBM Langflow OSS 1.0.0 through 1.11.5 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of command-line arguments in the MCP stdio server configuration...

CVE-2026-78575

IBM Langflow OSS 1.0.0–1.11.5 is vulnerable to OS command injection (CWE-78) in the MCP stdio server configuration , allowing a remote authenticated attacker to execute arbitrary commands. The root cause involves two gaps: the MCP stdio validator on Windows recognizes only one cmd.exe execution s...

PYSEC-2026-3812 Chainlit has command injection via MCP stdio transport that allows unauthenticated remote code execution

Am I affected? Only if your deployment sets features.mcp.enabled = true in .chainlit/config.toml. MCP has been disabled by default since v2.7.0, so most Chainlit deployments are not affected. No authentication is required: /mcp is reachable by any client that can open a session. Summary When MCP ...

Chainlit has command injection via MCP stdio transport that allows unauthenticated remote code execution

Am I affected?Only if your deployment sets features.mcp.enabled = true in .chainlit/config.toml. MCP has been disabled by default since v2.7.0, so most Chainlit deployments are not affected. No authentication is required: /mcp is reachable by any client that can open a session. SummaryWhen MCP is...

PT-2026-89614

Name of the Vulnerable Software and Affected Versions IBM Langflow OSS versions 1.0.0 through 1.11.5 Description Remote authenticated attackers can execute arbitrary commands due to improper validation of command-line arguments within the MCP stdio server configuration. Recommendations Update IBM...

CVE-2026-78575: Improper Neutralization of Special Elements used in an OS Command

IBM Langflow OSS 1.0.0 through 1.11.5 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of command-line arguments in the MCP stdio server configuration...

Security Bulletin: Langflow is vulnerable to arbitrary code execution due to multiple incomplete code security controls and missing execution guards

Summary Langflow uses a code security scanner and component-level execution policies to restrict server-side code execution to authorized users and contexts. The agentic assistant code scanner employs an incomplete denylist omitting process-spawning primitives and contains a logic error where...