Together AI reports prompt leakage from serverless inference requests
Tech

Together AI reports prompt leakage from serverless inference requests

TechNews Editorial
TechNews EditorialNov 22, 2026 · 1 min read
Share

Why it matters

Together AI is reviewing whether the downloaded prompts exposed sensitive personal information or other customer data.

The facts

  • Together AI says an unauthorized party downloaded stored prompt samples from June and July 2026 requests.
  • A credential exposed in the public xorl repository gave access to the private Hugging Face repository holding the samples.
  • Together AI says it is reviewing the samples and will contact affected customers directly as needed.

Advertisement

Together AI says an unauthorized party downloaded a subset of prompts submitted to its serverless inference service in June and July 2026. The company is reviewing the samples to determine what customer information was exposed and whom it needs to notify directly.

The samples came 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. Together AI says the samples were authorized for routine software testing and stored in a private Hugging Face repository.

An AI coding agent exposed the repository credential

According to the company, an AI coding agent committed a credential for that private repository while working on Together AI’s public xorl GitHub repository. Automated scanning detected the exposed credential, and the company reverted the commit. During the exposure window, an unauthorized party obtained the credential and used it to download the samples.

Together AI says the party searched the samples for credentials to other services and tested whether those credentials worked. Five of the credentials tested were canary credentials associated with a Dragos security experiment. The company says it has no reason to believe the prompt data was leaked further and understands that it has since been deleted.

A forensic investigator presses a red tamper-evident security seal onto a black briefcase clasp inside a glass building lobby.
Illustration: AI & Tech News

Together AI strengthened its security controls

Together AI says it has worked with an external forensic investigation firm and law enforcement. Its review has found no evidence of additional prompt leakage beyond this incident. The company also says it strengthened controls around development workflows, credentials and customer data. It advises customers handling sensitive prompt data to enable ZDR in their account settings.

The review of affected prompts is ongoing. Together AI says it will contact affected customers directly as needed with findings relevant to them.

What this means

The downloaded prompt samples originated from requests to MiniMax M3, GLM-5.2, and Kimi K2.6 models on June 24, July 4, July 8, and July 14, 2026. An unauthorized party searched the samples for credentials to other services and tested five canary credentials associated with a Dragos security experiment. Together AI worked with law enforcement and an external forensic investigation firm while advising customers handling sensitive prompt data to enable ZDR in their account settings. This disclosure follows Together AI's November 4, 2026 announcement of an inference optimization compiler and California's November 17, 2026 lawsuit against OpenAI regarding alleged AI agent security failures.

Source: Together AI

Newsletter

Get the best AI & tech news daily

A concise daily digest. Unsubscribe anytime.

We use your email only to send this newsletter.

Keep reading