ai infra guard

We have hosted the application ai infra guard in order to run this application in our online workstations with Wine or directly.

Quick description about ai infra guard:

AI-Infra-Guard (A.I.G.) is an open platform for auditing the security of artificial intelligence (AI) systems, developed by Tencent’s Zhuque Lab. It is designed to perform multi-level audits of AI infrastructure, agents, their capabilities, and large language models (LLMs) to identify vulnerabilities, risks, and potential attack vectors.

Features:

• ClawScan (OpenClaw Security Scan) — an OpenClaw security scan that identifies insecure configurations, risks related to staff qualifications, and checks for CVE vulnerabilities and leaks of confidential data.
• Agent-Scan is a multi-agent system for automated scanning of AI agent workflows (e.g., Dify, Coze).
• MCP Server and Agent Skill Scanning — Analyzes Model Context Protocol (MCP) servers and pluggable skills for risks such as tool poisoning, command interception, hidden code injection, and credential leakage. Supports scanning of source code or remote URLs.
• AI Infrastructure Vulnerability Scanning — Identifying AI infrastructure components (Ollama, vLLM, ComfyUI, n8n, Triton Inference Server, etc.) and comparing them against a database of known CVE vulnerabilities.
• Jailbreak resistance assessment — testing LBM for resistance to various attacks, including multi-stage methods (Many-Shot, PAIR, GOAT, ActorAttack).
• Open source. By default, there is no built-in authentication mechanism, so deploying the platform on public networks is not recommended. Cross-platform support (Linux, macOS, Windows) with Docker-based deployment. Integration capabilities via a web interface, REST API, and separate command-line utilities.

Programming Language: Go, Python, TypeScript.
Categories: