# genpark-prompt-injection-jailbreak-detector-skill

> genpark-prompt-injection-jailbreak-detector-skill — alphaparkinc-genpark-prompt-injection-jailbreak-detector-skill. Use this tool when you need to detect and prevent prompt injection and jailbreak attacks on AI systems, solving problems related to adversarial input and semantic manipulation. It analyzes input prompts and scores them for potential threats, providing output warnings and flags for suspicious patterns. Ideal for use in applications where AI security and integrity are critical, such as chatbots and virtual assistants.

Canonical page: https://skillsregistry.net/skills/alphaparkinc-genpark-prompt-injection-jailbreak-detector-skill  
JSON: https://api.skillsregistry.net/v1/skills/alphaparkinc-genpark-prompt-injection-jailbreak-detector-skill

## Description

GenPark AI Agent Skill - Heuristic and statistical prompt injection and jailbreak detector with semantic delimiter protection and adversarial pattern scoring.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## 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/alphaparkinc/genpark-prompt-injection-jailbreak-detector-skill)

## 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": "alphaparkinc-genpark-prompt-injection-jailbreak-detector-skill"
    }
  }
}
```

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