---
title: "Use models and data from trusted sources · Agent Wranglers"
url: https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/trusted-model-sources
updated: 2026-10-20
licence: "All rights reserved"
---

# Use models and data from trusted sources

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

- Level: Required
- Chapter: [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)
- Rule: Load models, adapters and training or search data only from sources you have reviewed, pinned by version or hash.
- How: Download models from the publisher's official account, and check the hash. Prefer safe file formats such as `safetensors` over pickle files that can run code. Review documents before they enter a search index, and record where each came from.
- Check: List every model file and index source in use. Each has a recorded source and hash, and no file is a pickle from an unknown publisher.

**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/trusted-model-sources`.

- Previous: [Accept only tokens issued for your MCP server](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/mcp-token-audience)
- Next: [Ground answers in your own data](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/grounded-answers)
- [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)