# Jailbreak Classifier

> Scores an inbound prompt for jailbreak/persona-override risk before the agent acts on it.

- Skill: `gl0di/jailbreak-classifier` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add gl0di/jailbreak-classifier`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gl0di/jailbreak-classifier/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: gl0di (https://skillmd.com/u/gl0di)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/gl0di/jailbreak-classifier

---


# Jailbreak Classifier

Scores an inbound prompt and returns a risk band so the calling agent can
decide whether to escalate to a human.

## Usage

```bash
python scripts/score_prompt.py < prompt.txt
```