bk99.de entertain the web since 1997

bk99.de
HF · SecurityCurated

A joint security analysis with Wiz

Summary

Hugging Face and Wiz Research examine the risks of loading foreign models and of isolated execution environments. The article shows how model artefacts can become a supply chain for executable code. Wiz Research reported security findings to Hugging Face.

Ideas

  • Models, demos and data sets together form a software supply chain.
  • Isolation must also take metadata, converters and custom code into account.

Insights

  • AI artefacts are active parts of the supply chain and need isolation, proof of origin and minimal privileges.

Facts

  • The collaboration led to fixes and additional protective measures.

Critique

  • A platform operator’s account does not replace independent disclosure of all findings.

Recommendations

  • Scan model artefacts, limit permissions and run foreign code only in isolation.

References

Read the original article on Hugging Face

Search the Web Archive

HF · 2026

Security incident at Hugging Face in July 2026

Hugging Face describes a break-in in which an autonomous agent combined a prepared data source with insecure execution paths. Internal data sets and credentials were reached; according to what was known at the time, public Hub artefacts were not manipulated. The attack combined a malicious data set with remote code execution and template injection.

HF · 2026

Why open AI matters for cybersecurity

The article argues that open models give defenders tools they can inspect and adapt. At the same time, it acknowledges that the same capabilities are available to attackers. Open weights allow local analysis without handing sensitive data to an API provider.

HF · 2024

The security architecture of Gradio 5

The security overview describes changes to file paths, network access and browser boundaries in Gradio 5. Public ML demos are thereby explicitly treated as web applications with an attack surface. Gradio 5 tightens the handling of accessible files and paths.