# sentinel-ai

> sentinel-ai — maxwellcalkin-sentinel-ai. Use this tool when you need to ensure the safety and security of large language model (LLM) applications in real-time, solving problems such as prompt injection, data leaks, and harmful content dissemination. The sentinel-ai tool provides 10 scanners with sub-millisecond latency, accepting LLM app inputs and outputting alerts and warnings through Python and TypeScript SDKs. Use it to protect your LLM apps from vulnerabilities and maintain a secure user experience.

Canonical page: https://skillsregistry.net/skills/maxwellcalkin-sentinel-ai  
JSON: https://api.skillsregistry.net/v1/skills/maxwellcalkin-sentinel-ai

## Description

Real-time AI safety guardrails for LLM apps. 10 scanners: prompt injection, PII, harmful content, code vulnerabilities, obfuscation detection. Sub-ms latency. Python + TypeScript SDKs. MCP proxy. Claude Code hooks.

## 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:** 2026-09-20

## Source

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

## 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": "maxwellcalkin-sentinel-ai"
    }
  }
}
```

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