# nuguard

> nuguard — nuguardai-nuguard. Use this tool when you need to evaluate the security of agentic AI applications and identify potential vulnerabilities. Nuguard provides core functionality for testing prompt injections, generating SBOMs, and performing static analysis, solving problems related to AI security and reliability. It takes in AI application code as input and outputs vulnerability assessments and security reports, ideal for use cases where securing AI applications is critical.

Canonical page: https://skillsregistry.net/skills/nuguardai-nuguard  
JSON: https://api.skillsregistry.net/v1/skills/nuguardai-nuguard

## Description

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

## Trust

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

## 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/NuGuardAI/nuguard)

## 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": "nuguardai-nuguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nuguardai-nuguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nuguardai-nuguard/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