# Adversa

> Use this tool when you need to identify and prioritize vulnerabilities in large language models, such as OWASP LLM Top 10 and MITRE ATLAS threats. Adversa scans for potential weaknesses and provides findings in various formats, including tables, JSON, SARIF, and via an MCP server. It helps AI agents and developers address security risks and improve the resilience of their LLM-based systems.

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

## Description

LLM red-team harness that scans for OWASP LLM Top 10 and MITRE ATLAS vulnerabilities, providing prioritized findings in table, JSON, SARIF, or via an MCP server for AI agents.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/m6mfc71xj4)
- **Repository:** <https://github.com/cognis-digital/adversa>

## 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-adversa"
    }
  }
}
```

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