Varbase Ai Safety
This project provides a comprehensive AI safety solution for Varbase, including AI logging with long-term retention and AI observability for transparency. It bundles 14 guardrail rules across three categories: Prompt Safety (Liability and Security) to block risky topics and malicious input, and PII Protection to detect and block personal information in AI interactions.
A recipe to bundle a complete AI safety stack for Varbase guardrails,
logging, and observability.
This recipe provides a defense-in-depth AI safety setup including:
- Drupal AI module
- AI Logging with 90-day retention enabled by default
- AI Observability for transparency and compliance reporting
- 14 guardrail rules across 3 sets, configured against
restrict_to_topicandregexp_guardrailplugins
Recipes Applied
This recipe chains the following upstream recipes via the recipes:
Included Guardrail Sets
Prompt Safety: Liability
Blocks topics that carry legal or reputational risk for the site owner.
- Liability: Legal Advice
- Liability: Medical Advice
- Liability: Sensitive Topics
Prompt Safety: Security
Blocks structurally malicious input and semantic prompt attacks
(XSS, HTML/CSS/JavaScript injection, prompt manipulation/jailbreak detection).
- Security: CSS Expression Injection
- Security: Dangerous HTML Tags
- Security: HTML Event Handler Injection
- Security: JavaScript Execution Functions
- Security: JavaScript Protocol
- Security: Prompt Manipulation
- Security: Script Tag Injection
PII Protection
Detects and blocks personally identifiable information (PII) in both user
input and AI output. Baseline GDPR / data-protection coverage.
- PII: Credit Card Number
- PII: Email Address
- PII: IBAN
- PII: Phone Number