---
title: "Use models and data from trusted sources · Agent Wranglers"
url: https://agentwranglers.se/playbook/application-security/supply-chain/trusted-model-sources
id: APS-77
level: Recommended
applies: ai-features
updated: 2026-10-27
build: a2a6bdfed830
tokens: 734
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Use models and data from trusted sources

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

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

- ID: APS-77
- Level: Recommended
- Chapter: [Supply chain](https://agentwranglers.se/playbook/application-security/supply-chain.md)
- Rule: Load models, adapters and training or search data only from sources you have reviewed, pinned by version or hash.
- 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.
- Applies when: The project uses AI models.
- How: Skip this rule when you only call a hosted model through its API. 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. [Pin the AI model version you depend on](https://agentwranglers.se/playbook/ai-features/prompts-as-code/pin-model-versions.md) once it is checked.

## Sources

- [OWASP LLM04:2026 Supply Chain](https://github.com/GenAI-Security-Project/GenAI-LLM-Top10/blob/main/2026/final/LLM04_SupplyChain.md)

## Related rules

- MLO-43 [Limit what any one source can put into training data](https://agentwranglers.se/playbook/machine-learning/training-data/poisoning-checks.md) in Machine learning
- MLO-21 [Keep every model in a registry with versions and aliases](https://agentwranglers.se/playbook/machine-learning/training-runs-and-the-registry/model-registry.md) in Machine learning
- MLO-42 [Store models in formats that cannot run code](https://agentwranglers.se/playbook/machine-learning/training-runs-and-the-registry/safe-model-formats.md) in Machine learning
- AIF-59 [Pin the AI model version you depend on](https://agentwranglers.se/playbook/ai-features/prompts-as-code/pin-model-versions.md) in AI features

**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/supply-chain/trusted-model-sources">Agent Wranglers application security playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Treat a machine that installed a bad package as breached](https://agentwranglers.se/playbook/application-security/supply-chain/compromised-package-response.md)
- Next: [Build releases at SLSA Build Level 2 or higher](https://agentwranglers.se/playbook/application-security/supply-chain/slsa-build-level.md)
- [Supply chain](https://agentwranglers.se/playbook/application-security/supply-chain.md)