How Deep Research Agents Can Leak Your Data
mediumnewsLLM-Specific
securityprivacy
Source: Embrace The RedAugust 24, 2025
Summary
Deep Research agents (AI systems that autonomously search and fetch information from multiple connected tools) can leak data between different connected sources because there is no trust boundary separating them. When an agent like ChatGPT performs research queries, it can freely use data from one tool to query another, and attackers can force this leakage through prompt injection (tricking an AI by hiding instructions in its input).
Classification
Attack Type
Data ExtractionPrompt Injection
Attack SophisticationModerate
Impact (CIA+S)
confidentiality
Affected Vendors
OpenAI
Related Issues
Original source: https://embracethered.com/blog/posts/2025/chatgpt-deep-research-connectors-data-spill-and-leaks/
First tracked: February 12, 2026 at 02:20 PM
Classified by LLM (prompt v3) · confidence: 85%