Last seen March 19, 2026

Amazon EKS Remote Code Execution Vulnerability

Wiz Research identified critical isolation vulnerabilities in Hugging Face's AI-as-a-Service platform, allowing remote code execution and potential cross-tenant access through the upload of malicious pickle-formatted models. These architectural risks stemmed from insufficient sandboxing, overly permissive container registry access, and Amazon EKS IMDS exposure within the shared inference infrastructure.

Technical Severity
Medium severity
Lifecycle Status

STABLE

What Happened

Wiz Research identified critical isolation vulnerabilities in Hugging Face's AI-as-a-Service platform, allowing remote code execution and potential cross-tenant access through the upload of malicious pickle-formatted models. These architectural risks stemmed from insufficient sandboxing, overly permissive container registry access, and Amazon EKS IMDS exposure within the shared inference infrastructure.

Why This Matters

The evidence matters to defenders using Amazon EKS because it could let an attacker run code in affected environments.

Recommended Action

Confirm whether BOMs is present in your environment and review vendor guidance for this report. Apply available patches or mitigations if your deployment matches the described conditions.

Exposure

My Interests Exposure

Exposure unknown

Recommended Response
Last Seen

Mar 19, 2026 05:30

Exposure reason: This incident does not currently match a technology in My Interests.

Exploitation status: DEMONSTRATED

Primary entities:

AmazonAmazon AWSHugging FaceAmazon EKSHugging Face's AI-as-a-Service platformRemote Code Execution

Timeline

  • Incident first seen
    Mar 19, 2026 05:30

    BugSkan first recorded this incident.

  • AI-BOMs: A Practical Guide to AI Bills of Materials - wiz.io
    Mar 19, 2026 05:30

    wiz.io · Vulnerability

Sources

AI-BOMs: A Practical Guide to AI Bills of Materials - wiz.io

wiz.io · Mar 19, 2026 05:30

Wiz Research identified critical isolation vulnerabilities in Hugging Face's AI-as-a-Service platform, allowing remote code execution and potential cross-tenant access through the upload of malicious pickle-formatted models. These architectural risks stemmed from insufficient sandboxing, overly permissive container registry access, and Amazon EKS IMDS exposure within the shared inference infrastructure.

Open publisher source

Other BugSkan incidents that share identifiers, products, or vendors with this report.

My Interests Match

Want personalized relevance?

Create an account to see which incidents overlap with your interests.

← Back to incident intelligence