# agenttax

> agenttax — cognis-digital-agenttax. Use this tool when you need to classify and mitigate AI-agent threats, leveraging Microsoft's AI-agent threat taxonomy to organize findings and implement effective countermeasures. It takes in threat findings as input and outputs classified threats with recommended mitigations, streamlining the threat analysis process. Ideal for security teams and researchers working with AI-agent threats, agenttax simplifies taxonomy-based threat classification and mitigation.

Canonical page: https://skillsregistry.net/skills/cognis-digital-agenttax  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-agenttax

## Description

Classify findings against Microsoft's AI-agent threat taxonomy with mitigations

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/cognis-digital/agenttax)

## 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": "cognis-digital-agenttax"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-agenttax` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-agenttax/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