Industry

Together AI reports prompt leak at serverless inference service from June-July 2026

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

AI summary

Together AI reported a security incident: after an AI coding agent committed credentials for a private Hugging Face repository to the public GitHub repository xorl, unauthorized parties downloaded stored prompt samples submitted between June and July 2026 to serverless inference services including MiniMax M3, GLM-5.2 and Kimi K2.6, and searched them for credentials of other services.

Key Takeaways

  • Together AI reported a security incident: after an AI coding agent committed credentials for a…
  • 2 and Kimi K2.
  • 6,and searched them for credentials of other services.

Quick Facts

Published
Updated
Source
Together AI 研究与产品博客(RSS)
Category
Industry
AI score
74
Read the original Read the full article at the original source
Why it matters

原文披露了提示词泄露的范围、成因与已落实的整改措施,用户可据此评估自己是否受影响及是否开启 ZDR。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Together AI reports prompt leak at serverless inference service from June-July 2026. November 21, 2026. https://new.nat6.net/en/news/xqe6lbb5zsjp9xbsc1o912cs0/

View all →