A full-stack AI Red Teaming platform for securing AI ecosystems with comprehensive scanning and evaluation.
AI-Infra-Guard is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view Tencent/AI-Infra-Guard --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
AI-Infra-Guard is a security platform that helps developers find and fix vulnerabilities in AI systems. It scans AI infrastructure, agents, skills, and LLMs for security issues like prompt injection and jailbreaks. The tool provides a user-friendly interface to automate AI security testing.
AI-Infra-Guard (A.I.G) is a full-stack AI Red Teaming platform developed by Tencent Zhuque Lab. It integrates multiple security scanning capabilities including OpenClaw Security Scan, Agent Scan, AI infrastructure vulnerability scan, MCP Server & Agent Skills scan, and LLM jailbreak evaluation. The platform aims to provide the most comprehensive, intelligent, and user-friendly solution for AI security risk self-examination. It supports various scanning modes such as ClawScan for web security, Skill Scanner for agent skills, and AIG Scanner for overall AI infrastructure. The tool is designed to help organizations proactively identify and mitigate security risks in their AI deployments, covering areas like prompt injection, data leakage, and unauthorized access. With a growing community and regular updates, AI-Infra-Guard is positioned as an industry-leading AI red teaming platform.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 52 days ago.
3841 GitHub stars indicate community interest.
7 open issues signal maintenance load.
Apache-2.0 license detected.
Scan AI infrastructure for vulnerabilities like open ports and misconfigurations.
Evaluate LLM jailbreak resistance and prompt injection risks.
Audit agent skills and MCP servers for security flaws.
Automate red teaming exercises for AI applications.
Integrate security scanning into CI/CD pipelines for AI projects.
Scanning may generate network traffic that could be flagged by intrusion detection systems.
Automated scanning might cause service disruption if not properly configured.
The tool itself should be kept updated to avoid false positives or missed vulnerabilities.
3,841
Stars
375
Forks
7
Issues
Apache-2.0
License
A terminal dashboard to monitor AI coding agents like Claude Code and Codex CLI in real-time.
A bridge between Streamable HTTP and stdio MCP transports, enabling flexible MCP server connectivity.
AI agent security scanner that detects vulnerabilities in agent configurations, MCP servers, and tool permissions.
A full-stack AI Red Teaming platform for securing AI ecosystems with comprehensive scanning and evaluation.
AI security engineers, DevOps engineers managing AI infrastructure, Red teamers and penetration testers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Scanning may generate network traffic that could be flagged by intrusion detection systems. Automated scanning might cause service disruption if not properly configured.
Similar or complementary options to evaluate include abtop, mcp-proxy, agentshield.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 3/5.