Tencent/AI-Infra-Guard — GitHub trending stats & insights

Featured

Bindu

Openhuman

Visit GitHub

Tencent/AI-Infra-Guard

#AI agent #AI infrastructure

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Python

3.8k

368

30 contributors

Apache License 2.0

website

Social mentions

Recent discussions about this repository across the web

一键解除Agent限制是Agent安全应该关注的话题，解除后Agent将完全执行用户指令，而无视system prompt/LLM自身的限制，执行任何命令。基于AIG可以检测Agent安全情况。

@w8ay1 · x.com

Most AI security tools test one thing. Tencent's new scanner covers the full stack. OpenClaw configs, agent perms, MCP servers, skills, infra, LLM endpoints — all of it. → 3.7K stars. BlackHat…

@agentxagi · x.com

Zero Trust assumes breach. Fine for networks. But who's auditing what an agent reads, writes, and sends mid-task? An agent that can browse, call APIs, and write files is an insider with no badge…

@DarshanSays · x.com

Repository activities

repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues

Social mentions

Repository activities

GitHub trending history