CVE-2026-41940-Exploit-PoC

CVE-2026-41940 Exploit POC 1. Führen Sie das Exploit-Skript aus und geben Sie das Ziel an python3 exploit.py --target https://example.com:2087/ 2. Sitzung erfassen und in Burp Suite wiedergeben Kopieren Sie den vom Skript generierten whostmgrsession-Wert Öffnen Sie die Ziel-URL im Browser von...

CVE-2026-18993 NousResearch hermes-agent Memory Toolset model_tools.py access control

A vulnerability was detected in NousResearch hermes-agent up to 0.16.0. Affected by this issue is some unknown functionality of the file hermes-agent/modeltools.py of the component Memory Toolset. The manipulation results in improper access controls. The attack can be executed remotely. The explo...

CVE-2026-67207 Wolf CMS 0.8.3.1 Authorization Bypass via BackupRestoreController

Wolf CMS through 0.8.3.1 contains an authorization bypass vulnerability in BackupRestoreController that allows authenticated non-administrative users to access restricted backup functionality due to a PHP operator precedence flaw in the permission check expression. Attackers can exploit the...

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

Impact LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token. The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key...

CVE-2026-64650

The CVE concerns the @ai-sdk/harness-opencode tool (HarnessV1 adapter backed by @openai/codex-sdk) that drives the codex CLI. Prior to version 1.0.29, it relayed requests from any process whose command line contained an allowed helper script path (Codex CLI shim), allowing untrusted sandbox code ...

CVE-2026-64651 AI SDK OpenCode Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path host-tool-mcp.mjs. This allows untrusted code executing in the...

CVE-2026-62207 OpenClaw < 2026.6.5 Authentication Bypass via Admin Tools

OpenClaw versions before 2026.6.5 contain an authentication bypass vulnerability that allows lower-trust callers to reach admin-scoped tools. Attackers can perform actions requiring stronger authorization by exploiting insufficient policy checks on configured input paths...

CVE-2026-62207 OpenClaw < 2026.6.5 Authentication Bypass via Admin Tools

OpenClaw versions before 2026.6.5 contain an authentication bypass vulnerability that allows lower-trust callers to reach admin-scoped tools. Attackers can perform actions requiring stronger authorization by exploiting insufficient policy checks on configured input paths...

CVE-2026-55605

DeepSeek MCP Server is an MCP server for DeepSeek V4. Starting in version 1.4.2 and prior to version 1.8.0, the self-hosted HTTP transport of @arikusi/deepseek-mcp-server exposes POST /mcp without any authentication: createMcpExpressApp is called without an authProvider and no middleware guards t...

GHSA-6FVR-66P3-3QJ4 OpenClaw: Hook-triggered CLI runs could receive owner MCP tool authority

Summary OpenClaw hook ingress can start automated agent runs using a configured hook token. In affected releases, a hook-triggered run could select a bundled CLI backend that received owner-scoped MCP loopback authority instead of a scope appropriate for hook ingress. This issue affects the...

Missing Authorization

Overview deeptutor is an An agent-native intelligent learning companion with multi-agent collaboration and RAG Affected versions of this package are vulnerable to Missing Authorization via the allowedmcptools function in deeptutor/multiuser/toolaccess.py. An attacker can gain unauthorized access ...

PT-2026-53919

DeepTutor before version 1.4.10 contains an authorization bypass vulnerability that allows low-privilege users to invoke unrestricted MCP tools due to the allowed mcp tools function returning None instead of a denied result when mcp tools is omitted from a user's grant in deeptutor/multi user/too...

OpenViking: Unauthenticated remote bot control via OpenAPI HTTP routes

OpenViking prior to commitc7bb167 contains an authentication bypass vulnerability in the VikingBot OpenAPI HTTP route surface where the authentication check fails open when the apikey configuration value is unset or empty. Remote attackers with network access to the exposed service can invoke...

PT-2026-53545

Summary OAuthManager.validate token returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. Details...

CVE-2026-11719

An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers. While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol...

CVE-2026-44301

Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node-based asset pipelines PostCSS, Babel, TailwindCSS, Hugo invoked the configured Node tools without restrictions on file system access. As a result, executing hugo against an untrusted site could...

DEBIAN-CVE-2026-44301

Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node-based asset pipelines PostCSS, Babel, TailwindCSS, Hugo invoked the configured Node tools without restrictions on file system access. As a result, executing hugo against an untrusted site could...

CVE-2026-44301 Hugo: Node tool execution allows file system access outside the project directory

Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node-based asset pipelines PostCSS, Babel, TailwindCSS, Hugo invoked the configured Node tools without restrictions on file system access. As a result, executing hugo against an untrusted site could...

CVE-2026-44301

Hugo is a static site generator. From 0.43 to before 0.161.0, when building a Hugo site that uses Node-based asset pipelines PostCSS, Babel, TailwindCSS, Hugo invoked the configured Node tools without restrictions on file system access. As a result, executing hugo against an untrusted site could...

Unspecified Vulnerability in PraisonAI (CNVD-2026-18147)

PraisonAI is a low-code multi-intelligence body collaboration framework by the individual developer Mervin Praison. PraisonAI suffers from a security vulnerability that stems from the OAuthManager.validatetoken function returning True for any token not found in its internal storage, which can be...