# assay

> assay — metahub-ai-assay. Use this tool when you need to verify the security and integrity of AI artifacts, such as skills, servers, and plugins, by inspecting code and running behavioral audits. Assay generates verifiable reports, providing a trust layer for AI ecosystems and helping to identify potential vulnerabilities. It integrates with git, allowing for seamless inspection and auditing of AI code repositories.

Canonical page: https://skillsregistry.net/skills/metahub-ai-assay  
JSON: https://api.skillsregistry.net/v1/skills/metahub-ai-assay

## Description

An open, reproducible trust layer for AI artifacts — skills, MCP servers, agents, and plugins. Assay inspects code, runs sandboxed behavioral audits, and generates verifiable reports. Help us build the open standard for AI ecosystem security.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/metahub-ai/assay)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "metahub-ai-assay"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/metahub-ai-assay` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/metahub-ai-assay/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt