# prompt-injection-detector

> Use this tool when you need to protect your AI agents from malicious input attacks, such as jailbreak attempts or instruction overrides. The Prompt Injection Detector scans input for potential threats, returning a confidence score, severity rating, and recommendation to block, warn, or pass. It's ideal for securing agent interactions with users, emails, documents, or other agents, and can be integrated via a pay-per-scan protocol with no API keys or subscriptions required.

Canonical page: https://skillsregistry.net/skills/found402-prompt-injection-detector  
JSON: https://api.skillsregistry.net/v1/skills/found402-prompt-injection-detector

## Description

Prompt Injection Detector is a stateless security microservice built for the agent economy. Before your agent acts on any input — whether from a user, an email, a document, or another agent — run it through this scanner first.
Detects: jailbreak attempts, instruction overrides, role-play manipulation, goal hijacking (OWASP ASI01), tool misuse patterns (OWASP ASI02), hidden instructions embedded in data, and indirect injection via external content.
Returns a confidence score, severity rating, specific patterns detected, and a clear recommendation — block, warn, or pass.
Pay per scan via x402 protocol. USDC on Base. No API keys. No subscriptions. No human in the loop. Agents call it directly.
MCP tool name: scan_for_injection

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/found402/prompt-injection-detector)

## 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": "found402-prompt-injection-detector"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/found402-prompt-injection-detector` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/found402-prompt-injection-detector/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