text moderation tool

The problem

User-generated content often contains toxic language, hate speech, or sensitive personal data that violates safety policies. Manually auditing text or misconfiguring moderation tools leads to security risks and inconsistent filtering.

What it does

• Identifies toxic language and hate speech within provided text strings.
• Detects personal data leaks to ensure privacy compliance.
• Manages session state and caching to optimize repeated moderation requests.
• Provides structured error handling for missing parameters or API rate limits.
• Audits domain and SSL configurations when triggered by specific infrastructure queries.

Frameworks & tools

Google Cloud NLP API, MCP (Model Context Protocol).

Why this beats prompting it yourself

Standard LLM prompting for moderation is prone to hallucinations and inconsistent safety thresholding. This skill connects to a specialized NLP moderation engine, manages stateful sessions, and handles infrastructure-specific audits like DNS and SSL verification that base models cannot perform reliably alone.

Use cases

• Audit domain configurations and SSL certificates for security compliance.
• Moderate user-generated comments or messages for toxicity.
• Scan text for accidental personal data exposure before storage.
• Verify SPF and DMARC records during website configuration audits.

Known limitations

Requires a valid GOOGLE_CLOUD_NLP_API_KEY configured in your environment variables. The tool relies on session IDs for state management between calls.