skilld
All skills
tencent avatar

/aig-scanner

@70c5b4d
by tencenttencent/ai-infra-guard6.7k stars
627

A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no plugin required. Requires AIG_BASE_URL to be configured. Triggers on: scan AI service, AI vulnerability scan, scan AI infra, check CVE, audit AI service, scan MCP, scan skills, audit AI tools, scan agent, red-team LLM, jailbreak test, 扫描AI服务, 检查AI漏洞, 扫描AI工具, 检查MCP安全, 审计Agent, 越狱测试.

Ask your Agent

Use this Skill: https://skilld.dev/gh/tencent/ai-infra-guard/aig-scanner

This session only. Nothing lands on disk.

README.md

≈546 tokens on demand. Your agent reads this file only when SKILL.md points to it.

A.I.G × OpenClaw — AI Security Scanning in One Chat Message

中文版

Invoke all A.I.G (AI-Infra-Guard) scanning capabilities directly from an OpenClaw chat — no A.I.G Web UI needed.

Prerequisite: A.I.G service is deployed (local or remote).

Install

clawhub install aig-scanner

Alternative:

Install this skill from source:
https://github.com/Tencent/AI-Infra-Guard/tree/main/skills/aig-scanner

ClawHub page:

https://clawhub.ai/aigsec/aig-scanner

Usage

After installation, just chat:

AI Infrastructure Scan — detect CVEs and misconfigurations in AI services (Ollama, vLLM, Dify, etc.)

Scan http://localhost:11434 for AI vulnerabilities

AI Tool / Skills Audit — audit MCP Servers, Agent Skills, and similar projects

Scan https://github.com/org/repo for AI tool security issues

AI Agent Scan — test A.I.G-configured Agents for authorization bypass, prompt injection, data leakage

Recommend configuring the Agent in A.I.G Web UI beforehand

Use A.I.G to scan agent demo-agent-id

LLM Safety Check — red-team test an LLM's jailbreak resistance

Use A.I.G to run a safety check on DeepSeek3.2

Notes

  • Recommended install path: use ClawHub.
  • Mainland China fallback: if ClawHub fails with Rate limit exceeded, install from the source directory in this repository.
  • A.I.G URL: configure AIG_BASE_URL on first install. This is required. Examples:
    • http://127.0.0.1:8088/
    • https://aig.example.com/
  • Auth: configure an API Key if A.I.G authentication is enabled; defaults to empty.
  • AI Tool / Skills Scan: requires an analysis model (model name, API key, base URL) — just tell OpenClaw on first use.
  • LLM Safety Check: requires both the target model and a separate evaluator model configuration. Provide target/eval model name, API key, and base URL.
  • Agent Scan: scans Agents already configured on the A.I.G platform; does not support parameter submission yet.

Powered by Tencent Zhuque Lab A.I.G

Source: SKILL.md on GitHub

Third-party checks

2 warnings4d4 checks · Risk SAFE
  • Gen Agent Trust Hub4d

    This skill provides a security auditing utility for AI infrastructure, tools, and agents, developed by Tencent Zhuque Lab. It interfaces with the AI-Infra-Guard (A.I.G) platform to perform various security scans and audits.

  • Socket4d

    1 alert: gptSecurity

  • Snyk4d

    Risk: MEDIUM · 1 issue

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 70c5b4d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 35 minutes ago.

Activeupdated 3 months ago

Capability

version
1.0.3
author
aigsec/Tencent Zhuque Lab
Other metadata
keywords
[
  "security",
  "scan",
  "audit",
  "ai-infra",
  "mcp",
  "skills",
  "agent",
  "jailbreak",
  "tencent-aig",
  "ai-infra-guard"
]
triggers
[
  "scan AI service",
  "scan AI infra",
  "check for CVE",
  "audit AI service",
  "scan MCP",
  "scan skills",
  "scan AI tools",
  "audit AI tools",
  "check MCP security",
  "scan agent",
  "audit agent",
  "red-team LLM",
  "jailbreak test",
  "check scan result",
  "扫描AI服务",
  "检查AI漏洞",
  "扫描模型服务",
  "扫描AI工具",
  "检查MCP安全",
  "审计AI工具",
  "扫描Agent",
  "越狱测试",
  "评测模型抗越狱",
  "查看扫描结果"
]
metadata
{
  "openclaw": {
    "emoji": "🛡️",
    "requires": {
      "bins": [
        "python3"
      ]
    },
    "primaryEnv": "AIG_BASE_URL",
    "skillKey": "aig-scanner"
  },
  "aig": {
    "homepage": "https://github.com/Tencent/AI-Infra-Guard/"
  }
}

README badge

README badge for tencent/ai-infra-guard/aig-scanner