~ / directory / hugging-face
HF
Mixed · Foundation Models · reviewed 2026-04

Hugging Face

The ML community hub. Key attack surface.

Visit huggingface.co
01

What it does

The largest open-source ML community hub hosting models, datasets, and spaces. Provides model discovery, evaluation, and deployment tools. The primary distribution channel for open-source AI models.

02

Security relevance

Hugging Face is the biggest AI supply chain attack surface. Poisoned models, malicious datasets, and compromised model files are real threats (LLM03, LLM05). Anyone can upload models, and verification mechanisms are still maturing. Security teams need to understand the risks of pulling models from Hugging Face.

03

When to use it

Use for model discovery and evaluation, but implement supply chain verification before deploying any model from Hugging Face. Check model provenance, scan for malicious code in model files, and validate model behaviour before production use.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 2 in LLM, 1 in Agentic.

LLM Top 10 · 2025 · 2/10 covered
01
02
03
04
05
06
07
08
09
10
Agentic Top 10 · 2026 · 1/10 covered
01
02
03
04
05
06
07
08
09
10
05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: Hugging Face
slug: hugging-face
type: Mixed
category: Foundation Models
url: https://huggingface.co

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  [LLM03, LLM05]
  asi:  [ASI04]

complexity:    Guided Setup
pricing:       —
audience:      Builder
lifecycle:     [augment]

tags: [ML, Models, Open Source]