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.

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow AI-Infra-Guard

AI-Infra-Guard Web Site

Other Useful Business Software

MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.

Start Free

Rate This Project

User Ratings

5.0 out of 5 stars

★★★★★

★★★★

★★★

★★

★

ease 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5

features 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5

design 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5

support 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 5 / 5

User Reviews

Filter Reviews:

All

tencent54 Posted 2026-08-23

The best platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.