ml-content-classifier

Classifies text for toxicity, prompt injection, and jailbreak attempts using ML models.

1|Updated Feb 8, 2026

Search Tags:#AI classification #prompt injection #content safety #jailbreak prevention #toxicity detection

Ready to run

npx skills add https://github.com/framerslab/agentos-skills --skill ml-content-classifier

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ml-content-classifier
Source: https://github.com/framerslab/agentos-skills/tree/main/registry/curated/ml-content-classifier
Command: npx skills add https://github.com/framerslab/agentos-skills --skill ml-content-classifier

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill ensures content safety by providing real-time classification against toxicity, prompt injection, and jailbreak attempts, helping you maintain a secure digital environment.

Core Features & Use Cases

Toxicity Check: Identify and prevent toxic language and hate speech.
Prompt Injection Defense: Mitigate the risk of unauthorized instruction overrides.
Jailbreak Detection: Guard against role-play attacks and system manipulations.
Use Case: Use the ml-content-classifier to ensure the content shared within your organization adheres to high safety standards and compliance guidelines.

Quick Start

Apply the ml-content-classifier to classify a piece of text with 'classify_content("User input text").'

Frequently Asked Questions about ml-content-classifier

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect prompt injection attempts in AI systems?▼

Detect prompt injection attempts by applying ML classification models like BERT and ONNX to analyze input text and identify unauthorized instruction overrides in real time.

What is the best way to prevent jailbreak attacks and toxic content in text moderation?▼

Preventing jailbreak attacks and toxic content involves utilizing an ML-driven content safety classifier to detect role-play manipulations and hate speech, ensuring your digital environment maintains strict compliance.

Do I need specific ML models to run content safety classification?▼

Yes, you need ML classification models like BERT and ONNX for runtime prediction to execute content safety classification and accurately evaluate text for toxicity and system breaches.

How do I classify a piece of text for toxicity and system breaches?▼

Classify text for toxicity and system breaches by calling the classify_content function with your user input text, which leverages ML models to provide real-time safety predictions.

Can I use this ML content classifier for compliance and content moderation across platforms?▼

Yes, you can use this ML content classifier for compliance and content moderation across platforms, as it provides in-depth text analysis applicable in security settings to maintain high safety standards.