CVE-2026-55640 Nextcloud MCP Server: Unauthenticated `POST /webhooks/nextcloud` allows arbitrary vector data deletion when `WEBHOOK_SECRET` is unset ( default )

Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance. Prior to 0.117.2, the POST /webhooks/nextcloud endpoint in nextcloudmcpserver/vector/webhookreceiver.py has no authentication by default because WEBHOOKSECRET defaults to None and startup...

CVE-2026-55640

Nextcloud MCP Server prior to 0.117.2 contains an authentication bypass in the POST /webhooks/nextcloud endpoint. The WEBHOOK_SECRET defaults to None and startup validation does not enforce it, allowing unauthenticated requests to handle_nextcloud_webhook(). The payload["user"]["uid"] field is at...

EUVD-2026-65596

Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance. Prior to 0.117.2, the POST /webhooks/nextcloud endpoint in nextcloudmcpserver/vector/webhookreceiver.py has no authentication by default because WEBHOOKSECRET defaults to None and startup...

CVE-2026-55581 mcp-shell: Secure Mode Allowlist Bypass via Default `/bin/bash` Executable

mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, the default Docker security.yaml includes /bin/bash in allowedexecutables, while security.go validates only the first token and checkBlockedPatternsAndCommands does not reject the shell...

CVE-2026-55532 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream validateorigin uses requestorigin.startswithallowed, allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests...

Claude-Code-MCP-Injection-PoC

Claude Code: Travisamento del Prompt di Conferma dello Strumento MCP Una Proof-of-Concept PoC professionale che dimostra una vulnerabilità critica dell'interfaccia utente/UX in Claude Code di Anthropic. Questa vulnerabilità consente a un server MCP malevolo di indurre gli utenti ad approvare...

toolbox

-Significant%20AI%2C%20fully%20reviewed-1f77b4 MCP-basierte Tools für Anwendungssicherheitstests für deinen Coding-Agenten. Kein Scanner – eine kollaborative Werkbank. Agenten tun sich schwer mit UI und zustandsbehafteten APIs; du bist in beidem gut. Sectool ermöglicht es dir, eine Anwendung über...

Malicious-MCP

Böswilliger MCP Dies ist ein Proof-of-Concept-Projekt, mit dem Sie einen MCP-Server bereitstellen können, der sich als jeder andere MCP-Server „tarnt". Dieser MCP fungiert als MCP „Proxy" und leitet einfach alle eingehenden Anfragen an einen vorgeschalteten MCP-Server weiter. Was ist ein MCP? Ein...

CVE-2026-53509 @aborruso/ckan-mcp-server: SSRF via base_url allows access to internal networks (Potential fix bypass of CVE-2026-33060)

CKAN MCP Server is a tool for querying CKAN open data portals. A known vulnerability CVE-2026-33060 indicated tools including ckanpackagesearch and sparqlquery that accept a baseurl parameter had the risk of making HTTP requests to arbitrary endpoints without restriction. A fix was applied to...

CVE-2026-53509

@aborruso/ckan-mcp-server (an MCP server for querying CKAN open data portals) is vulnerable to SSRF prior to version 0.4.106 . The validateServerUrl hostname check in src/utils/http.ts only blocked the literal string localhost, but hostname aliases such as ip6-localhost and ip6-loopback (defined ...

CVE-2026-53509 @aborruso/ckan-mcp-server: SSRF via base_url allows access to internal networks (Potential fix bypass of CVE-2026-33060)

CKAN MCP Server is a tool for querying CKAN open data portals. A known vulnerability CVE-2026-33060 indicated tools including ckanpackagesearch and sparqlquery that accept a baseurl parameter had the risk of making HTTP requests to arbitrary endpoints without restriction. A fix was applied to...

CVE-2026-62316

Microsoft UFO open-source framework for intelligent automation across devices and platforms. Prior to 3.0.8, ufo/client/mcp/httpservers/linuxmcpserver.py binds a FastMCP streamable HTTP server to localhost:8010 but does not validate the Host, Origin, or Sec-Fetch-Site headers. An...

CVE-2026-62674

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

CVE-2026-62674

Omnigent (open-source AI agent framework) prior to 0.3.0 is vulnerable to an authenticated Remote Code Execution via the PUT /sessions/{session_id}/agent endpoint. The endpoint validates LEVEL_EDIT permission for the session but fails to reject a bound shared or template agent whose agent.session...

CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

EUVD-2026-64016

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

CVE-2026-54449

LangBot is a global IM bot platform designed for LLMs. In version 4.10.7 and earlier, any authenticated user can add or change an STDIO MCP server configuration without an adequate authorization boundary. In src/langbot/pkg/provider/tools/loaders/mcp.py, StdioServerParameters accepts the configur...

EUVD-2026-63480

LangBot is a global IM bot platform designed for LLMs. In version 4.10.7 and earlier, any authenticated user can add or change an STDIO MCP server configuration without an adequate authorization boundary. In src/langbot/pkg/provider/tools/loaders/mcp.py, StdioServerParameters accepts the configur...

CVE-2026-18482

Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax and runPlaywrightTest functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS...