概览
What is A.I.G (AI-Infra-Guard)?
A.I.G (AI-Infra-Guard) is an AI Red Teaming Platform developed by Tencent Zhuque Lab. It integrates capabilities such as ClawScan, Agent Scan, AI infrastructure vulnerability scanning, MCP Server & Agent Skills scanning, and Jailbreak Evaluation. The platform is designed for developers and security teams to perform comprehensive self-examination of AI security risks across models, agents, and infrastructure.
How to use A.I.G (AI-Infra-Guard)?
Deploy with Docker: clone the repository, run docker-compose -f docker-compose.images.yml up -d, then access the web interface at http://localhost:8088. For a one‑click installation, use curl https://raw.githubusercontent.com/Tencent/AI-Infra-Guard/refs/heads/main/docker.sh | bash. A.I.G can also be invoked from OpenClaw via the aig-scanner skill by installing it with clawhub install aig-scanner and configuring AIG_BASE_URL. The platform currently has no authentication and must not be deployed on public networks.
Key features of A.I.G (AI-Infra-Guard)
- ClawScan: One‑click evaluation of OpenClaw security risks.
- Agent Scan: Multi‑agent framework for AI agent workflow security.
- MCP Server & Agent Skills scan: Detects 14 major security risk categories.
- AI infra vulnerability scan: Identifies 100+ AI components and 1900+ CVEs.
- Jailbreak Evaluation: Assesses prompt security with multiple attack methods.
- Free and open source under Apache 2.0 license.
Use cases of A.I.G (AI-Infra-Guard)
- Scan a locally running vLLM instance for
