Together AI Reports Prompt Leakage Incident from June-July 2026

News


Together AI disclosed a security breach involving prompt samples from its serverless inference service in June and July 2026, caused by credential exposure.




Thematic editorial illustration
Editorial illustration; not a product screenshot or event photograph

Together AI has disclosed a security incident involving the unauthorized access and download of prompt samples from its serverless inference service during June and July 2026. The breach occurred after a credential for a private repository was inadvertently exposed in a public GitHub repository. The company is currently investigating the scope of the incident and notifying affected customers as necessary.

Details of the Incident

According to Together AI, the issue stemmed from routine software testing that involved storing authorized prompt samples in a private Hugging Face repository. These samples originated from requests to the MiniMax M3, GLM-5.2, and Kimi K2.6 models, primarily on June 24, July 4, July 8, and July 14, 2026. During the development of the public GitHub repository “xorl,” an AI coding agent inadvertently committed a credential granting access to the private repository.

The exposed credential was detected by automated scanning tools, and the commit was promptly reverted. However, during the exposure window, an unauthorized party accessed the repository and downloaded the stored prompt samples. The party reportedly searched the samples for additional credentials and tested five canary credentials associated with a Dragos security experiment. Together AI stated that it has no evidence of further data dissemination and believes the unauthorized party has since deleted the data.

Investigation and Response

Together AI has engaged an external forensic investigation firm and law enforcement to assess the breach. While no additional prompt leakage has been identified beyond this incident, the company is still reviewing the affected data to determine whether sensitive personal information or other customer data was exposed. Customers impacted by the breach will be contacted directly.

In response to the incident, Together AI has implemented several measures to enhance security, including:

  • Using scoped or short-lived credentials and keyless access where possible to limit the impact of credential exposure.
  • Implementing checks for credentials in all pull requests.
  • Making zero data retention (ZDR) the default setting for new accounts.
  • Updating development processes to govern the use of AI coding agents.

Recommendations for Customers

Together AI advises customers handling sensitive prompt data to enable zero data retention (ZDR) in their account settings. For further inquiries regarding the incident, customers can contact the company at [email protected].

Vipul Ved Prakash, CEO and Co-founder of Together AI, issued an apology for the incident and reaffirmed the company’s commitment to improving its security practices to prevent similar occurrences in the future.

Share with your friends!

Products You May Like

Leave a Reply

Your email address will not be published. Required fields are marked *

Please enter CoinGecko Free Api Key to get this plugin works.