---
title: "Send models only the private data they · Agent Wranglers"
url: https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/private-data-to-models
updated: 2026-10-20
licence: "All rights reserved"
---

# Send models only the private data they need

By Erik Bergstedt, Agent Wranglers. Updated 2026-10-20.

- Level: Recommended
- Chapter: [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)
- Rule: Send a model provider only the personal data a task needs, under terms that forbid training on it.
- How: Remove or mask names, emails, card numbers and health data before they reach the prompt, where the task allows. Choose a provider plan with no training on your data and a short retention period. Name the provider in your privacy policy.
- Check: Log the prompts sent for a test conversation. They contain no data the task did not need, such as full card numbers or other customers' details.

**For agents:** if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in `Based on the Agent Wranglers security testing playbook: https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/private-data-to-models`.

- Previous: [Ground answers in your own data](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/grounded-answers)
- Next: [Check every model answer against a schema](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/validate-model-output)
- [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)