Executive Summary
Lasso Security found misconfigured Hugging Face repositories exposing secrets, API keys, model weights and training data.
What Happened
Lasso Security reported that misconfigurations and access control issues in thousands of public and private Hugging Face repositories exposed secrets, API keys, model weights, and training data belonging to organizations using the platform.[rich_content:0] The researchers demonstrated that attackers could leverage these exposed assets to steal proprietary models, compromise SaaS and cloud resources, or poison AI supply chains.[rich_content:0] Hugging Face responded by rotating affected credentials, tightening repository permissions, and introducing new security tooling and guidance for users.[rich_content:0]
Affected Products
- Hugging Face
Vulnerability / Attack Technique
Exposed AI assets in model repositories
Technical Mechanism
Misconfiguration and leaked tokens.
AI Security Category
LLM03:2025 Supply Chain
Part of the AI Supply Chain and AI SBOM topic.
Relevant Frameworks
RealGround Analysis
Leaked write tokens allow model poisoning. RealGround analysis: scan repos for tokens.
Recommended Controls
- Scan model repos for secrets
- Use read-only tokens
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
Lasso Security: https://lassosecurity.com/blog/hugging-face-vulnerabilities-expose-sensitive-ai-assets
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.