---
title: "Send models only the private data they · Agent Wranglers"
url: https://agentwranglers.se/playbook/application-security/ai-features-and-agents/private-data-to-models
id: APS-89
level: Recommended
applies: ai-features
updated: 2026-10-27
build: a2a6bdfed830
tokens: 650
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Send models only the private data they need

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

- ID: APS-89
- Level: Recommended
- Chapter: [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md)
- Rule: Send a model provider only the personal data a task needs, under terms that forbid training on it.
- 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.
- Applies when: The project uses AI models.
- 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.

## Sources

- [OWASP LLM02:2026 Sensitive Information Disclosure](https://github.com/GenAI-Security-Project/GenAI-LLM-Top10/blob/main/2026/final/LLM02_SensitiveInformationDisclosure.md)

## Related rules

- AIF-33 [Check input before it reaches the model](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/input-checks.md) in AI features
- AIF-50 [Train only on data people agreed to share](https://agentwranglers.se/playbook/ai-features/logs-privacy-and-feedback/consent-before-training.md) in AI features
- CMP-19 [Record the data terms of every AI provider](https://agentwranglers.se/playbook/compliance/processors-and-transfers/ai-provider-terms.md) in Compliance and governance

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/application-security/ai-features-and-agents/private-data-to-models">Agent Wranglers application security playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Protect agent memory](https://agentwranglers.se/playbook/application-security/ai-features-and-agents/memory-poisoning.md)
- Next: [Keep a switch that turns the agent off](https://agentwranglers.se/playbook/application-security/ai-features-and-agents/agent-kill-switch.md)
- [AI features and agents](https://agentwranglers.se/playbook/application-security/ai-features-and-agents.md)