Skip to content
AI News HubLIVE
Original source2 min read

Security event: Prompt leakage for requests in June and July of 2026

Summary

Together AI disclosed a security incident where an AI coding agent exposed a credential to a private Hugging Face repository, allowing an unauthorized party to download prompt samples from June and July 2026. The company has implemented remediation measures and strengthened security controls.

Security event: Prompt leakage for requests in June and July of 2026
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

All blog posts

Company

Published 11/21/2026

Security event: Prompt leakage for requests in June and July of 2026

Authors

Vipul Ved Prakash

Table of contents

40+ Models Chosen for Production...40+ Models Chosen for Production...40+ Models Chosen for Production...

We are notifying customers about a security incident involving a subset of prompts submitted to Together AI’s serverless inference service in June and July 2026. An unauthorized party downloaded stored prompt samples after a credential for a private repository was exposed in a public code repository.

We apologize for this incident. We are reviewing the affected data to determine what information was exposed and which customers require direct notification.

What happened

As part of routine software testing, we collected prompt samples authorized for that use and stored them in a private Hugging Face repository. The samples came from requests to the Minimax M3, GLM 5.2, and Kimi 2.6 models, primarily on June 24, July 4, July 8, and July 14, 2026.

During development of our public GitHub repository, xorl, an AI coding agent committed a credential that provided access to the private Hugging Face repository. Our automated scanning detected the exposed credential, and we reverted the commit.

During the exposure window, an unauthorized party obtained the credential and used it to download the stored prompt samples. The party subsequently searched those samples for credentials to other services and tested whether those credentials were valid. Five of the credentials tested were canary credentials associated with a Dragos security experiment.

We have no reason to believe the unauthorized party has leaked this data further and understand that it has now been deleted.

Investigation and scope

We have worked with an external forensic investigation firm and law enforcement to investigate the incident.

Based on our review, we have not identified evidence of additional prompt leakage beyond this incident. Our review of the affected prompt contents is ongoing to determine whether sensitive personal information or other customer data was exposed. We will contact affected customers directly as needed with the findings relevant to them.

Changes we have made

Following the incident, we strengthened controls around development workflows, credentials, and customer data. These changes include:

Using scoped or short-lived credentials, and keyless access where supported, to reduce the potential impact of credential exposure.

Checking all pull requests for credentials.

Making zero data retention (ZDR) the default setting for new accounts.

Updating our development processes governing the use of AI coding agents.

What customers can do

Customers handling sensitive prompt data should enable ZDR in their account settings.

If you have questions about this incident or its potential impact on your organization, contact [email protected].

‍

Vipul Ved Prakash

CEO and Co-founder, Together AI

Related articles

View All

View All

Key points and analysis

Article intelligence

EngineersIntermediate

Key points

  • The leak occurred when an AI coding agent committed a credential to a public GitHub repository, providing access to a private Hugging Face repository.
  • Affected prompts came from requests to the Minimax M3, GLM 5.2, and Kimi 2.6 models, primarily on June 24, July 4, July 8, and July 14, 2026.
  • Together AI has worked with an external forensic firm and law enforcement; no evidence of additional prompt leakage has been found.
  • The company has implemented improvements including scoped/short-lived credentials, scanning all pull requests for credentials, and making zero data retention (ZDR) the default for new accounts.

Highlights and analysis are generated automatically and may contain errors. Check the original source.