RepoAI
Browse MCPs

Edgeone Clawscan

100TrustedInstructions only

Automated security audits and threat intelligence for your OpenClaw environment.

What it does

Edgeone Clawscan acts as an oversight layer for your AI agent environment. By monitoring your installed skills and local configurations, it helps identify potential vulnerabilities or unauthorized changes that might escape manual review.

This skill bridges the gap between static local files and real-time threat intelligence. When active, it cross-references your current setup against a database of known security advisories, ensuring your assistant operates within a framework validated by recent threat research.

When it earns its place

Reach for it when…

Use this to perform routine health checks on your OpenClaw installation or when you need to vet a new skill before integrating it into your workflow. It is particularly valuable for teams that prioritize proactive risk management and need a reliable way to verify the integrity of their AI components on a regular basis.

Look elsewhere when…

This is not a replacement for comprehensive system-level network monitoring or operating system firewalls. It does not analyze your proprietary data, private chat transcripts, or workspace files for sensitive leaks, nor does it provide real-time runtime prevention against arbitrary code execution.

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 health check on my OpenClaw environment
  • Scan my installed skills for potential vulnerabilities
  • Perform a security audit of this new skill
  • Check my current OpenClaw setup for security risks

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/edgeone-clawscan ~/.claude/skills/edgeone-clawscan

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/edgeone-clawscan .claude/skills/edgeone-clawscan

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

Edgeone Clawscan changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →