AIG Scanner

100TrustedShips scripts

AI infrastructure and agent security analysis for local or remote deployments.

What it does

Aig Scanner integrates your assistant with Tencent Zhuque Lab's AI-Infra-Guard to identify potential vulnerabilities within your AI services. By triggering automated safety assessments, the skill assesses infrastructure, tool configurations, and agent behavior, reporting findings directly within your chat interface. It enables your assistant to act as a security analyst, performing targeted evaluations without requiring you to switch environments.

Installing this skill allows the assistant to execute specialized diagnostic scripts against your specified targets. It handles the communication with your designated scanning server, translates complex results into readable summaries, and manages the lifecycle of your security queries, ensuring that infrastructure audits and agent testing happen on-demand as part of your existing conversational flow.

When it earns its place

Reach for it when…

Apply this skill when you need to audit local service endpoints, verify the security posture of an agent configuration file, or conduct a jailbreak evaluation of a specific model before deployment.

Look elsewhere when…

Do not use this for ongoing, continuous security monitoring or background logging, as this skill is designed for discrete, point-in-time assessments rather than persistent surveillance.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • Run a security audit on my local agent configuration
  • Can you check this AI service for infrastructure vulnerabilities
  • Evaluate the safety of this GitHub repository for tools
  • Perform a jailbreak test on the target model

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/Tencent/AI-Infra-Guard.git /tmp/AI-Infra-Guard
mkdir -p ~/.claude/skills
cp -r /tmp/AI-Infra-Guard/skills/aig-scanner ~/.claude/skills/aig-scanner

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/AI-Infra-Guard/skills/aig-scanner .claude/skills/aig-scanner

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server