Skip to main content
Xoxoday applies input validation, filtering, and sanitization controls to mitigate prompt injection risks.
Xoxoday applies input validation, filtering, and sanitization controls to mitigate prompt injection risks. Since the platform calls frontier model APIs rather than running its own models, prompt injection controls are implemented at the application layer: (1) Prompt templates are predefined and constrained, limiting the scope of user-influenced input, (2) User inputs are validated and sanitized before being included in API calls, (3) Output filtering is applied to AI responses before they are displayed to users, (4) Security testing of AI features, including prompt injection scenarios, is included in the regular VAPT and application security testing cycles. Learn more: Empuls Help Centre

Is the AI / LLM model tested to prevent model poisoning?

Not directly applicable (Xoxoday does not train or host AI models). Xoxoday does not train, retrain, or host AI/LLM models…

Is the AI / LLM model tested to prevent sensitive data disclosure?

Xoxoday implements controls to prevent sensitive data disclosure through AI features: (1) Input filtering: Prompts sent to frontier model APIs are…