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
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.
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/