# promptscan

> Use this tool when you need to detect and prevent prompt injection attacks on AI agents, scanning user input, documents, and tool outputs to identify potential threats. It solves problems related to AI security and data integrity by providing a score, attack type, and sanitized text output. The tool takes in user input and returns injection detection results, making it ideal for use cases where AI model security is a top priority.

Canonical page: https://skillsregistry.net/skills/nicks-brn-promptscan  
JSON: https://api.skillsregistry.net/v1/skills/nicks-brn-promptscan

## Description

Production-ready prompt injection detection for AI agents. Scan user input, retrieved docs, and tool outputs before passing them to an LLM. Returns injection_detected, score, attack_type, and sanitized text.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-05-14

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-16

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/nicks-brn/promptscan)

## 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": "nicks-brn-promptscan"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nicks-brn-promptscan` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nicks-brn-promptscan/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