CVE-2026-69263 Flowise: CVE-2025-8943 Patch Bypass: npm_config_yes bypasses MCP environment variable blocklist (Unauthenticated RCE)

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the mitigation for CVE-2025-8943 blocked -y and --yes flags on npx, but packages/components/nodes/tools/MCP/core.ts denied only PATH, LDLIBRARYPATH, DYLDLIBRARYPATH, and NODEOPTIONS by exact...

Malicious code in @or-sdk/mcp-tools (npm)

npm/@or-sdk/mcp-tools is affected by the large-scale, self-propagating npm supply-chain worm of 2026-08-04 the "Shai-Hulud: Here We Go Again" wave — the same campaign that began with the compromise of the keyv and cacheable maintainer account. The listed versions were trojanized and republished b...

MAL-2026-11713 Malicious code in @or-sdk/mcp-tools (npm)

npm/@or-sdk/mcp-tools is affected by the large-scale, self-propagating npm supply-chain worm of 2026-08-04 the "Shai-Hulud: Here We Go Again" wave — the same campaign that began with the compromise of the keyv and cacheable maintainer account. The listed versions were trojanized and republished b...

CVE-2026-18655 Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt Injection

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

CVE-2026-18655

CVE-2026-18655 affects awslabs.amazon-mq-mcp-server (MCP) prior to 2.0.24. The issue is an improper restriction of endpoints in the RabbitMQ broker connection tools, allowing a remote unauthenticated actor (via prompt injection) to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access ...

EUVD-2026-52406

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

toolbox v0.2.2

-Significant%20AI%2C%20fully%20reviewed-1f77b4 MCP-based application security testing tools for your coding agent. Not a scanner — a collaborative workbench. Agents struggle with UI and stateful APIs; you're good at both. Sectool lets you explore an application through its proxy while an agent...

CVE-2026-68578 ArcadeDB before 26.7.3 Authentication Bypass via MCP Transport

ArcadeDB versions before 26.7.3 fail to bind the authenticated principal in the MCP HTTP transport, causing all engine permission checks to silently pass as no-ops. Non-root MCP-allowed users can perform arbitrary database writes, DDL, schema mutations, and execute arbitrary JavaScript code via t...

CVE-2026-68578

ArcadeDB before 26.7.3 is affected by an authentication bypass in the MCP HTTP transport: the server does not bind the authenticated principal, causing engine permission checks to pass as no-ops. As a result, non-root MCP-allowed users can perform arbitrary writes, DDL, schema mutations, and run ...

EUVD-2026-51987

ArcadeDB versions before 26.7.3 contain an information disclosure vulnerability in the MCP getserversettings tool that leaks the arcadedb.ha.clusterToken in cleartext. Attackers with MCP access can retrieve the cluster token and use it with X-ArcadeDB-Cluster-Token and X-ArcadeDB-Forwarded-User...

SecureAI-Scan v0.7.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

CVE-2026-67336

better-auth versions before 1.6.11 contain insecure cryptographic defaults in the oidcProvider and mcp plugins that advertise the none algorithm and accept plain PKCE by default. Attackers can exploit algorithm negotiation to accept unsigned tokens or intercept authorization codes when PKCE plain...

EUVD-2026-51816

better-auth versions before 1.6.11 contain insecure cryptographic defaults in the oidcProvider and mcp plugins that advertise the none algorithm and accept plain PKCE by default. Attackers can exploit algorithm negotiation to accept unsigned tokens or intercept authorization codes when PKCE plain...

CVE-2026-67333

better-auth before 1.6.13 and pre-release builds 1.7.0-beta.0 through 1.7.0-beta.3 fail to validate the scheme of redirecturis registered via the deprecated oidc-provider plugin and the mcp plugin which wraps the same provider. An attacker can register an OAuth client with a javascript:...

EUVD-2026-51810

better-auth before 1.6.13 and pre-release builds 1.7.0-beta.0 through 1.7.0-beta.3 fail to validate the scheme of redirecturis registered via the deprecated oidc-provider plugin and the mcp plugin which wraps the same provider. An attacker can register an OAuth client with a javascript:...

Malicious code in refbase-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 745c419d7f3a6fbe38ef076e64076ca81735ccf43395f2bb6296b4d8ffca794f Package published as 'refbase-mcp' self-describes as 'install-email-research'. The postinstall hook loads lib/report.js which, when a consent flag is...

Malicious code in hit-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a87a289453b876b0dae6773dc57ed8fff3f935d293bf9256287af064d6f2bfa3 lib/report.js imports childprocess, fs, https, and os, reads local files via fs.readFileSync, gathers host identity via os.hostname and os.userInfo,...

MAL-2026-11477 Malicious code in refbase-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 745c419d7f3a6fbe38ef076e64076ca81735ccf43395f2bb6296b4d8ffca794f Package published as 'refbase-mcp' self-describes as 'install-email-research'. The postinstall hook loads lib/report.js which, when a consent flag is...

MAL-2026-11466 Malicious code in hit-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a87a289453b876b0dae6773dc57ed8fff3f935d293bf9256287af064d6f2bfa3 lib/report.js imports childprocess, fs, https, and os, reads local files via fs.readFileSync, gathers host identity via os.hostname and os.userInfo,...

Malicious code in mcp-server-boilerplate (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 50ee88b53e786db18609f7956c556a7f814b476c895bb90d5663aedc82ca14f0 Package name 'mcp-server-boilerplate' is unrelated to the Model Context Protocol ecosystem it evokes; the shipped code is a data-collection payload...