AI-Infra-Guard
A full-stack AI red team platform providing security scanning and assessment.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 4.0k
- Source
- skill-github
- Repository
- github.com/Tencent/AI-Infra-Guard
Overview
AI-Infra-Guard is a full-stack AI red team platform developed by Tencent Zhuque Lab. It offers comprehensive, intelligent, and user-friendly self-inspection solutions for AI security risks through features such as OpenClaw security scanning, Agent scanning, skill scanning, MCP scanning, AI infrastructure scanning, and LLM jailbreak evaluation. This capability helps detect and remediate potential security vulnerabilities in AI systems, enhancing overall system security. Suitable for enterprises and developers needing AI security assessments.
Capabilities
- ▪OpenClaw security scanning
- ▪Agent scanning
- ▪Skill scanning
- ▪MCP scanning
- ▪AI infrastructure scanning
- ▪LLM jailbreak evaluation
Use cases
Setup
Refer to the official documentation for installation and configuration: https://tencent.github.io/AI-Infra-Guard/
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with AI-Infra-Guard?
Please visit the official documentation and follow the quick start guide.
What types of scanning are supported?
Supports OpenClaw security scanning, Agent scanning, skill scanning, and more.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.