CVE-2026-114090

The Trigger.dev cli-v3 (versions 3.0.0 before 4.5.4 ) is vulnerable to a missing authentication flaw in the trigger dev --mcp server. The server binds to all network interfaces, exposing the /sse and /messages endpoints. This allows LAN attackers or malicious web pages to send MCP tools/call requ...

EUVD-2026-106893

Trigger.dev cli-v3 from 3.0.0 before 4.5.4 contains a missing authentication vulnerability in the trigger dev --mcp server, which binds all network interfaces and exposes the /sse and /messages endpoints. LAN attackers or malicious web pages can send MCP tools/call requests to invoke trigger-task...

sandbox-agent

Agents Agent infrastructure from Rivet. Join us on Discord. Projects Project| Directory| Docs ---|---|--- Rivet Agents : run agents such as Pi as durable Rivet Actors @rivet-dev/pi, @rivet-dev/sandbox-adapter| packages/, docs in docs/| rivet.dev/agents/docs Sandbox Agent : run coding agents in...

firecrawl-mcp-server

Firecrawl MCP Server A Model Context Protocol MCP server that brings Firecrawl, the context API for AI agents, to MCP-compatible clients: search, scrape, and interact with the live web and get back clean Markdown or structured data. Big thanks to @vrknetha, @knacklabs for the initial...

damn-vulnerable-MCP-server

Cursor SSE Compatibility for Damn Vulnerable MCP This document provides an overview of the updates made to the Damn Vulnerable Model Context Protocol DVMCP project to make it compatible with Cursor's Server-Sent Events SSE implementation. Overview The original DVMCP project has been enhanced to...

MCP-Inspector-CVE-2025-49596

MCP Inspector CVE-2025-49596 Vulnerability Checker This script checks if an MCP Inspector server is vulnerable to CVE-2025-49596, a security issue where the /sse endpoint responds to unauthenticated requests missing auth token. How It Works The script sends a GET request to the /sse endpoint of t...

GitLab MCP Server < 2.1.27 - Unauthenticated SSE Transport Access

The @zereight/mcp-gitlab GitLab MCP server exposes its SSE transport endpoints without any authentication when SSE mode is enabled. An unauthenticated attacker with network access can establish an MCP session and invoke every registered tool, including uploadmarkdown, which reads arbitrary files...

CVE-2026-109437

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST...

EUVD-2026-104570

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST...

CVE-2026-109437 Cognition < 0.13.0 Unauthenticated RCE via Local Shell Backend

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST...

CVE-2026-109437 Cognition < 0.13.0 Unauthenticated RCE via Local Shell Backend

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST...

CVE-2026-109437

The Cognition software (versions prior to 0.13.0 ) is vulnerable to unauthenticated remote code execution (RCE) . The root cause is the lack of authentication on the REST/SSE API combined with the agent sandbox backend defaulting to local execution . An attacker can exploit this by creating a ses...

POC-CVE-2026-93680

Description Proof of concept exploit code for CVE-2026-93680 Usage Step 1: Connect to MCP SSE terminal 1 Step 2: Initialize MCP session and list MCP tools terminal 2 Step 3: Bypass auth and exfiltrate data terminal 1, output result of step 2...

aiobotocore (0.2.3), aiobotocore-botorange (>=0.1.0, <=0.2.3a0) +9 more potentially affected by CVE-2026-111064 via aiohttp (1.3.5)

aiohttp PYPI version 1.3.5 is affected by a known vulnerability. The following packages have a transitive dependency on aiohttp and may be impacted: - aiobotocore 0.2.3 - aiobotocore-botorange =0.1.0, =0.0.3a0, =1.2.0, =1.0.0, =3.0.2, =3.0.5 Source cves: CVE-2026-111064 Source advisory:...

aiobotocore (0.2.3), aiobotocore-botorange (>=0.1.0, <=0.2.3a0) +9 more potentially affected by CVE-2026-111063 via aiohttp (1.3.5)

aiohttp PYPI version 1.3.5 is affected by a known vulnerability. The following packages have a transitive dependency on aiohttp and may be impacted: - aiobotocore 0.2.3 - aiobotocore-botorange =0.1.0, =0.0.3a0, =1.2.0, =1.0.0, =3.0.2, =3.0.5 Source cves: CVE-2026-111063 Source advisory:...

pentest-mcp

Pentest MCP Professional penetration-testing MCP server with modern transport/auth support and expanded recon tooling. What Changed in 0.9.0 Upgraded MCP SDK to @modelcontextprotocol/sdk@^1.26.0 Kept MCP Inspector at the latest release @modelcontextprotocol/inspector@^0.20.0 with bundled launcher...

undici: undici: Denial of Service via memory exhaustion in EventSource client

A flaw was found in undici. A malicious server can trigger a Denial of Service DoS by exhausting application memory. When an application connects to an untrusted Server-Sent Events SSE feed, the EventSource parser does not properly limit retained internal state when processing fragmented lines or...

undici: undici: Denial of Service via memory exhaustion in EventSource client

A flaw was found in undici. A malicious server can trigger a Denial of Service DoS by exhausting application memory. When an application connects to an untrusted Server-Sent Events SSE feed, the EventSource parser does not properly limit retained internal state when processing fragmented lines or...

studio

ShipSec Studio Open-Source Security Workflow Orchestration Platform. ShipSec is currently in active development. We are optimizing the platform for stable production use and high-performance security operations. ShipSec Studio provides a visual DSL and runtime for building, executing, and...

CVE-2026-109924

A flaw was found in undici. A malicious server can trigger a Denial of Service DoS by exhausting application memory. When an application connects to an untrusted Server-Sent Events SSE feed, the EventSource parser does not properly limit retained internal state when processing fragmented lines or...