> ## Content Index
> Fetch the complete content index at: https://nordisk-ai.ghost.io/llms.txt
> Use this file to discover other available public pages before exploring further.

# DeepSeek Leaked Sensitive Information
- URL: https://nordisk-ai.ghost.io/deepseek-leaked-sensitive-information/
- Published: 2025-03-04T20:59:04.000Z
- Updated: 2026-08-27T14:59:42.000Z
- Description: A serious security flaw at Chinese AI startup DeepSeek exposed over a million chat logs and sensitive data - completely unprotected. How many AI companies actually have similar security holes?
- Author: Anders Hagen
- Tags: Cybersecurity, #Migrated-1787841634512, #wp, #wp-post, #Import 2026-08-27 14:41, #Import 2026-09-07 13:41

Security researchers at **Wiz Research** have discovered a serious security flaw at the Chinese AI startup **DeepSeek**. A publicly accessible **ClickHouse database** exposed over a million log entries, including chat logs, secret API keys, and internal backend details.

### Full Access Without Authentication

Wiz Research identified that the database, accessible via **oauth2callback.deepseek.com:9000** and **dev.deepseek.com:9000**, was completely unprotected and allowed full control over the data content. The flaw meant anyone could:

Gain access to internal **chat logs and system data**

Read and use **secret keys** and API access

Modify or delete data in the database

DeepSeek, which recently gained major attention for its **DeepSeek-R1** model, an AI system that challenges OpenAI's models in performance and cost-efficiency, took immediate action after Wiz Research reported the security hole.

### Lacking Security in the AI Industry

The discovery highlights a larger problem in the AI industry - **the lack of robust security measures** around sensitive databases. AI startups handle enormous amounts of sensitive information, making them attractive targets for cyberattacks.

[Read a More In-Depth Article Here](https://www.wiz.io/blog/wiz-research-uncovers-exposed-deepseek-database-leak?ref=nordisk-ai.ghost.io)