# A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories

arXiv: https://arxiv.org/abs/2505.01067 · HTML: https://mlsanity.com/paper/2505.01067/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 6 of 6)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry](https://mlsanity.com/paper/2303.02552/) (2023)
- [Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs](https://mlsanity.com/paper/2409.09368/) (2024)
- [Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders](https://mlsanity.com/paper/2406.03508/) (2024)

## Built on by (most cited first, 2 of 2)

- [Formal Analysis and Supply Chain Security for Agentic AI Skills](https://mlsanity.com/paper/2603.00195/) (2026)
- [Securing the AI Supply Chain: What Can We Learn From Developer-Reported Security Issues and Solutions of AI Projects?](https://mlsanity.com/paper/2512.23385/) (2025)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by the public, face significant security challenges; in particular, configuration files originally intended to set up models by specifying parameters and initial settings can be exploited to execute unauthorized code, yet research has largely overlooked their security compared to that of the models themselves; in this work, we present the first comprehensive study of malicious configurations on Hugging Face, identifying three attack scenarios (file, website, and repository operations) that expose inherent risks; to address these threats, we introduce CONFIGSCAN, an LLM-based tool that analyzes configuration files in the context of their associated runtime code and critical libraries, effectively detecting suspicious elements with low false positive rates and high accuracy; our extensive evaluation uncovers thousands of suspicious repositories and configuration files, underscoring the urgent need for enhanced security validation in AI model hosting platforms.