---
id: "nr-prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac"
slug: "prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac"
type: "raw_signal"
title: "Prompts sent to model providers stay stored after the request ends"
description: "Together AI says an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July, using a credential exposed in a public code repository."
observed_at: "2026-11-22"
record_date: "2026-11-22"
date_kind: "observed_at"
novelty: "notable"
source_platform: "newruntime.com"
topics: ["prompts"]
entities: ["Together AI","MiniMax M3","GLM-5.2","Kimi K2.6","Hugging Face","Dragos","xorl","Vipul Ved Prakash","Ted Tschopp","OpenAI"]
related_patterns: ["agent-security-moves-to-runtime-boundaries"]
source_url: "https://www.together.ai/blog/security-event-prompt-leakage-for-requests-in-june-and-july-of-2026"
source_urls: ["https://www.together.ai/blog/security-event-prompt-leakage-for-requests-in-june-and-july-of-2026","https://tedt.org/The-AI-Finished-its-Job-Three-Days-Later-Something-Re-opened-the-Link","https://support.google.com/gemini/answer/13594961?hl=en"]
why_it_matters: "Together AI says an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July, using a credential exposed in a public code repository. Dragos found that tracking links planted in AI requests were opened again days later. Google says Gemini keeps chats for about two months even with History off. Builders should treat anything sent to a provider as stored data with its own exposure risk."
verification_level: "source-linked"
signal_type: "synthesis"
synthesis_of: [{"slug":"security-event-prompt-leakage-for-requests-in-june-74b417","title":"Security event: Prompt leakage for requests in June and July of 2026","url":"https://newruntime.com/posts/security-event-prompt-leakage-for-requests-in-june-74b417/"},{"slug":"the-ai-finished-its-job-three-days-later-55114e","title":"The AI Finished its job. Three Days Later, Something Re-opened the Link.","url":"https://newruntime.com/posts/the-ai-finished-its-job-three-days-later-55114e/"},{"slug":"google-retains-gemini-temporary-chats-and-history-off-e3ed5f","title":"Google retains Gemini temporary chats and History-off conversations for about two months","url":"https://newruntime.com/posts/google-retains-gemini-temporary-chats-and-history-off-e3ed5f/"}]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac"
retrieval_nugget: "Together AI says an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July, using a credential exposed in a public code repository."
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac/","markdown":"https://newruntime.com/signals/prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac.md","json":"https://newruntime.com/signals/prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac.json"}
markdown_url: "https://newruntime.com/signals/prompts-sent-to-model-providers-stay-stored-after-the-request-ends-754fac.md"
---

# Prompts sent to model providers stay stored after the request ends

## Retrieval answer

Together AI says an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July, using a credential exposed in a public code repository.

Together AI says an unauthorized party downloaded stored samples of prompts sent to its serverless inference service in June and July, using a credential exposed in a public code repository. Dragos found that tracking links planted in AI requests were opened again days later. Google says Gemini keeps chats for about two months even with History off. Builders should treat anything sent to a provider as stored data with its own exposure risk.

From the Field Notes:

- [Security event: Prompt leakage for requests in June and July of 2026](https://newruntime.com/posts/security-event-prompt-leakage-for-requests-in-june-74b417/) (2026-11-22)
- [The AI Finished its job. Three Days Later, Something Re-opened the Link.](https://newruntime.com/posts/the-ai-finished-its-job-three-days-later-55114e/) (2026-11-22)
- [Google retains Gemini temporary chats and History-off conversations for about two months](https://newruntime.com/posts/google-retains-gemini-temporary-chats-and-history-off-e3ed5f/) (2026-11-21)

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Prompts](https://newruntime.com/topics/prompts.md): Explore the prompts topic hub.
- collection: [Signals](https://newruntime.com/signals.json): Open the signals and the raw-signal archive.
- collection: [Sources](https://newruntime.com/sources/): See the original sources this archive cites.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)
