aimap

AIMap Internet-scale discovery and security testing platform for exposed AI agent infrastructure. AIMap finds, fingerprints, and security-tests publicly exposed AI endpoints — MCP servers, Ollama instances, vLLM/LiteLLM proxies, LangServe chains, Gradio apps, ComfyUI nodes, and more. Think Shodan...

skills

SpecterOps Skills Reusable agent skills, plugins, and agent definitions for SpecterOps. Use With Codex Each plugin includes a Codex manifest at .codex-plugin/plugin.json. codex plugin marketplace add /Users//Projects/skills or codex plugin marketplace add SpecterOps/skills Then open Codex and...

mcp-server-attestation

Part of theStudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it mcp-server-attestation Layer-2 supply-chain hardening for Model Context Protocol servers. Ed25519-signed tool manifests, runtime spawn-attestation, default-deny argument sanitizer. Direct response to: OX Security...

seclab-taskflows

GitHub Security Lab Taskflows This repository contains example taskflows to use with the SecLab Taskflow Agent, as well as the custom MCP servers that are needed to run the taskflows. Quick start Go to https://github.com/GitHubSecurityLab/seclab-taskflows and start a codespace. Wait a few minutes...

mcp-xray

MCP X-Ray !NOTE Looking to secure AI agent skills? Check out Skill X-Ray, an open-source static security scanner that analyzes skill packages for malicious or risky behavior before installation, without executing them. Overview MCP X-Ray is a unified open-source security scanning and penetration...

CVE

CVE's Table CVE Number| Type| Company/Product| Description| Article Link| Repository Link ---|---|---|---|---|--- CVE-2026-9680| SQLi| Alibaba RDS MCP Servers| TBA| TBA| TBA CVE-2026-50335| LPE| Windows July 2026| TBA| TBA| TBA GHSA-73cv-556c-w3g6| SQLi| Apache Pinot MCP 3.1.0| Missing sanitizati...

pkgxray

pkgxray — pre-install security for npm packages, MCP servers, and AI agents Inspect an npm package or MCP server before you install or connect to it, and get a deterministic, evidence-backed SAFE, REVIEW, or BLOCK verdict. Local, zero-dependency static analysis — normal scans never execute packag...

agent-opfor

Open-source adversary emulation for AI agents, LLM apps, and MCP servers. Test your AI like a real attacker would — from your CLI, your IDE, or a browser extension that anyone on your team can use. Website · Docs · GitHub · Browser Extension · Discord OPFOR is short for Opposition Force — a...

agent-scan

Snyk Agent Scan Discover and scan agent components on your machine for prompt injections and vulnerabilities including agents, MCP servers, skills. Note: We don't publish an npm package for Agent Scan. Install it via uvx or as a standalone binary. Note: CLI output is experimental and subject to...

LLM-MCP-Security-Field-Guide

🛡️ AI Security Field Guide — LLM + MCP Security The most comprehensive, up-to-date, practitioner-first security reference for LLM applications and Model Context Protocol MCP deployments. Covers real CVEs, live attack patterns, OWASP frameworks, red teaming tools, and actionable checklists — update...

CVE-2026-88755

Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted repository...

PT-2026-115623

Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted repository...

EUVD-2026-102905

Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted repository...

CVE-2026-88755

Z.ai ZCode v3.11.2.6792 was discovered to automatically establish connections with MCP servers declared inside a repository's workspace configuration, possibly allowing attackers to execute arbitrary code via opening a crafted repository...

CVE-2026-108856

UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the...

CVE-2026-108856 UnicomAI Wanwu through 0.6.5 Authorization Bypass via /v1/appspace/app/key AppKey Minting

UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the...

CVE-2026-108856

The UnicomAI Wanwu software through version 0.6.5 is vulnerable to an authorization bypass (CWE-639) via the POST /v1/appspace/app/key endpoint. This flaw allows authenticated users to mint AppKeys bound to other users' MCP servers by providing a victim's MCP server UUID and setting the appType t...

CVE-2026-108856 UnicomAI Wanwu through 0.6.5 Authorization Bypass via /v1/appspace/app/key AppKey Minting

UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the...

PT-2026-110175

Name of the Vulnerable Software and Affected Versions UnicomAI Wanwu versions prior to 0.6.6 Description An authorization bypass allows authenticated users to mint AppKeys bound to MCP servers belonging to other users. By sending a request to the endpoint "/v1/appspace/app/key" and providing a...

CVE-2026-108856: Authorization Bypass Through User-Controlled Key

UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the...